Summary of your 'study carrel' ============================== This is a summary of your Distant Reader 'study carrel'. The Distant Reader harvested & cached your content into a collection/corpus. It then applied sets of natural language processing and text mining against the collection. The results of this process was reduced to a database file -- a 'study carrel'. The study carrel can then be queried, thus bringing light specific characteristics for your collection. These characteristics can help you summarize the collection as well as enumerate things you might want to investigate more closely. This report is a terse narrative report, and when processing is complete you will be linked to a more complete narrative report. Eric Lease Morgan Number of items in the collection; 'How big is my corpus?' ---------------------------------------------------------- 55 Average length of all items measured in words; "More or less, how big is each item?" ------------------------------------------------------------------------------------ 6268 Average readability score of all items (0 = difficult; 100 = easy) ------------------------------------------------------------------ 54 Top 50 statistically significant keywords; "What is my collection about?" ------------------------------------------------------------------------- 55 user 7 contact 5 system 5 Twitter 4 model 4 COVID-19 3 Bluetooth 2 query 2 location 2 health 2 game 2 app 1 virtual 1 value 1 trial 1 trait 1 topic 1 time 1 tcn 1 tablet 1 smartphone 1 simulation 1 security 1 section 1 seal 1 score 1 scooter 1 ride 1 review 1 retina 1 relation 1 recommendation 1 question 1 proposal 1 processing 1 privacy 1 post 1 positive 1 political 1 player 1 platform 1 personality 1 openness 1 object 1 network 1 mood 1 mental 1 level 1 italian 1 interviewing Top 50 lemmatized nouns; "What is discussed?" --------------------------------------------- 5071 user 1252 datum 1067 model 1029 information 1019 system 1012 contact 818 time 741 health 735 app 657 network 593 device 588 number 587 approach 539 location 537 study 528 method 524 result 506 case 463 % 419 feature 409 recommendation 409 platform 397 privacy 394 tracing 391 use 389 individual 383 value 383 application 360 people 341 - 335 level 331 performance 329 example 319 community 317 service 317 analysis 310 design 309 risk 304 security 304 query 296 research 292 interaction 274 task 274 set 274 proximity 274 data 272 embedding 264 work 264 server 261 algorithm Top 50 proper nouns; "What are the names of persons or places?" -------------------------------------------------------------- 427 al 351 et 261 • 257 COVID-19 240 Bluetooth 233 . 184 Fig 179 u 179 Twitter 168 VR 107 Table 107 ML 100 ID 93 t 91 IT 83 Health 77 Google 74 U 69 GCG 67 iPad 67 T 67 Facebook 62 Android 61 Social 60 j 57 A 55 C 54 MAB 53 Data 52 Model 52 GPS 51 m 51 IR 49 K 49 DCTS 48 sha 48 Sect 48 RSSI 48 AP 47 Quantum 47 China 46 nan 46 iOS 46 User 46 DOI 44 S 44 Provo 42 Information 42 Easy 41 WiFi Top 50 personal pronouns nouns; "To whom are things referred?" ------------------------------------------------------------- 2675 we 1386 it 792 they 381 i 332 them 104 you 99 he 95 us 63 one 53 themselves 43 itself 39 she 25 me 24 him 16 u 13 her 5 's 4 oneself 4 himself 3 s 3 ours 3 myself 1 δs 1 theirs 1 qcomp 1 pseudonyms 1 ourselves 1 ndcg@10 1 infectedusercheckin 1 f Top 50 lemmatized verbs; "What do things do?" --------------------------------------------- 10293 be 1979 have 1778 use 905 base 655 do 645 provide 567 show 402 trace 387 make 364 propose 361 follow 359 identify 358 include 336 consider 326 find 323 learn 294 give 285 collect 267 require 267 generate 264 allow 262 take 261 see 252 need 242 perform 242 help 218 present 217 represent 213 relate 211 infect 209 compare 205 exist 204 report 200 share 198 contain 196 define 195 describe 194 get 193 create 184 increase 182 improve 177 obtain 177 apply 175 support 169 focus 167 test 166 design 165 receive 161 understand 161 know Top 50 lemmatized adjectives and adverbs; "How are things described?" --------------------------------------------------------------------- 1339 not 782 such 723 also 717 more 652 other 591 social 541 different 486 only 483 - 442 well 407 high 404 however 382 then 382 first 322 most 305 positive 270 same 269 e.g. 264 many 263 new 258 mobile 257 public 257 large 234 thus 233 specific 232 infected 226 as 214 further 209 negative 205 even 202 available 201 mental 193 several 189 online 183 good 182 out 181 therefore 181 long 178 real 176 possible 176 low 170 current 167 second 167 non 165 personal 162 similar 155 particular 152 important 151 various 145 very Top 50 lemmatized superlative adjectives; "How are things described to the extreme?" ------------------------------------------------------------------------- 99 good 88 most 59 least 36 high 33 Most 28 late 15 large 12 big 11 near 8 bad 6 weak 6 great 5 low 4 small 4 early 3 new 2 tough 2 strong 2 simple 2 safe 2 long 2 leftmost 2 hard 2 grave 2 close 2 -which 1 âăÿweak 1 wifilocationharv 1 wide 1 slight 1 short 1 shaky 1 quick 1 fast 1 eld 1 easy 1 cord-223669-hs5pfg4b 1 MAB)-driven 1 Least 1 A.16 1 -there Top 50 lemmatized superlative adverbs; "How do things do to the extreme?" ------------------------------------------------------------------------ 234 most 27 least 10 well 1 worst Top 50 Internet domains; "What Webbed places are alluded to in this corpus?" ---------------------------------------------------------------------------- 3 www.newsguardtech.com 2 www.tensorflow.org 2 github.com 1 www.scienceathome.org 1 www.protezionecivile.gov.it 1 www.gleamviz.org 1 www.example.com 1 wifitrace.github.io 1 pallicovid.app 1 expressiveinterviewing.org 1 en.wikipedia.org 1 doi.org 1 cutt.ly 1 creativecommons.org 1 chatbots.org 1 botlist.co 1 balsamiq.com Top 50 URLs; "What is hyperlinked from this corpus?" ---------------------------------------------------- 2 http://www.tensorflow.org/api 2 http://www.newsguardtech.com/ 1 http://www.scienceathome.org/ 1 http://www.protezionecivile.gov.it/ 1 http://www.newsguardtech.com/ratings/rating-process-criteria/ 1 http://www.gleamviz.org/simulator/ 1 http://www.example.com/index.html 1 http://wifitrace.github.io 1 http://pallicovid.app/ 1 http://github.com/halgurd18/lockdown 1 http://github.com/LCS2-IIITD/RETINA 1 http://expressiveinterviewing.org 1 http://en.wikipedia.org/wiki/Domain_name 1 http://doi.org/XXX 1 http://cutt.ly/TdOzKPm 1 http://creativecommons.org/licenses/bync/4.0/ 1 http://chatbots.org 1 http://botlist.co 1 http://balsamiq.com Top 50 email addresses; "Who are you gonna call?" ------------------------------------------------- 2 li.tong@huawei.com 2 kayhan@ieee.org 1 yy@hhhealth.org 1 wzaman@juniv.edu 1 weiyaqianbit@foxmail.com 1 up-date@facebookmail.com 1 shovon.sylhet@gmail.com 1 shenmeng@bit.edu.cn 1 shantoroy@ieee.org 1 rbuyya@unimelb.edu.au 1 laszka.aron@gmail.com 1 info@pathcheck.org 1 hossainmdrazon@gmail.com 1 alistair.barros@qut.edu.au 1 first.last@koyauniversity.org Top 50 positive assertions; "What sentences are in the shape of noun-verb-noun?" ------------------------------------------------------------------------------- 20 contact tracing apps 10 user does not 9 contact tracing system 8 contact trace data 8 use is not 7 contact tracing app 7 contact tracing service 7 information is not 7 user is not 6 health use cases 6 users do not 5 approach is not 5 model performs significantly 5 users are able 5 users are not 4 contact tracing application 4 contact tracing interviews 4 contact tracing tool 4 method does not 4 users are more 3 approach does not 3 apps are available 3 contact tracing data 3 contact tracing graph 3 contact tracing solutions 3 contact tracing strategies 3 contact tracing systems 3 contact tracing technology 3 models are also 3 people are not 3 study did not 3 system does not 3 system is able 3 systems use handheld 3 user is able 3 user needs help 2 app is currently 2 app is not 2 app is very 2 approach is highly 2 approach is similar 2 approach is specifically 2 approaches do not 2 approaches require quick 2 apps do not 2 case is depressed 2 case is not 2 contact trace service 2 contact tracing experiment 2 contact tracing interview Top 50 negative assertions; "What sentences are in the shape of noun-verb-no|not-noun?" --------------------------------------------------------------------------------------- 4 approach is not only 2 case is not depressed 2 information is not available 1 app is not widely 1 data are not available 1 data is not necessary 1 features are not available 1 individuals is not possible 1 information is not already 1 information is not only 1 methods are not scalable 1 model is not robust 1 model is not sensitive 1 network is not distinguishable 1 networks do not actively 1 people are not sufficiently 1 result was not strictly 1 studies was not large 1 study did not explicitly 1 system are not officially 1 system is not only 1 systems is not directly 1 time does not necessarily 1 tracing does not directly 1 tracing has no significant 1 tracing is not straightforward 1 use is not necessarily 1 use is not typically 1 user is not actively 1 users do not accurately 1 users do not simply 1 users have no direct 1 users have no explicit 1 users is not feasible 1 users were not aware A rudimentary bibliography -------------------------- id = cord-227156-uy4dykhg author = Albanese, Federico title = Predicting Shifting Individuals Using Text Mining and Graph Machine Learning on Twitter date = 2020-08-24 keywords = Twitter; individual; topic; user summary = Moreover, this machine learning framework allows us to identify not only which topics are more persuasive (using low dimensional topic embedding), but also which individuals are more likely to change their affiliation given their topological properties in a Twitter graph. Using graph topological information and detecting topics of discussion of the first network, we built and trained a model that effectively predicts when an individual will change his/her community over time, identifying persuasive topics and relevant features of the shifting users. Given that our objective was to identify shifting individuals and persuasive arguments, we implemented a predictive model whose instances are the Twitter users who were active during both time periods [34] and belonged to one of the biggest communities in both time periods networks. In this paper we presented a machine learning framework approach in order to identify shifting individuals and persuasive topics that, unlike previous works, focused on the persuadable users rather than studying the political polarization on social media as a whole. doi = nan id = cord-026948-jl3lj7yh author = Amini, Hessam title = Towards Explainability in Using Deep Learning for the Detection of Anorexia in Social Media date = 2020-05-26 keywords = attention; user summary = Results show that the weights assigned by the user-level attention strongly correlate with the amount of information that posts provide in showing if their author is at risk of anorexia or not, and hence can be used to explain the decision of the neural classifier. Previous work in NLP for clinical psychology has typically used this type of attention mechanism to create a representation of social media users: a collection of online posts from each user is fed to the model and the inter-document attention (also referred to as user-level attention) creates a representation of the user through a weighted average of the representations of their online posts, with the most informative posts are assigned higher weights. In this paper, we propose a quantitative approach, specifically focused on the user-level (inter-document) attention mechanism in a binary classification task of detection of a specific mental health issue, anorexia. In this work, we proposed a quantitative approach to validate the explainability of the user-level attention mechanism for the task of the detection of anorexia in social media users based on their online posts. doi = 10.1007/978-3-030-51310-8_21 id = cord-243596-ryyokrdx author = Baron, Lauren title = When Virtual Therapy and Art Meet: A Case Study of Creative Drawing Game in Virtual Environments date = 2020-10-16 keywords = game; user; virtual summary = In a mixed-design study, healthy participants (N=16, 8 females) completed one of the easy or hard trajectories of the virtual therapy game in standing and seated arrangements using a virtual-reality headset. The results from participants'' movement accuracy, task completion time, and usability questionnaires indicate that participants had significant performance differences on two levels of the game based on its difficulty (between-subjects factor), but no difference in seated and standing configurations (within-subjects factor). In this paper, we introduce a creative drawing game for virtual therapy and investigate user''s comfort, range of motion and movement in multiple scenarios and configurations in a pilot study. The working hypothesis of this study was that our creative drawing VR game would be effective when integrated into therapy by analyzing improved Task Completion Time (TCT), accuracy based on lower number of the mistakes, and user experience (UX). doi = nan id = cord-000332-u3f89kvg author = Broeck, Wouter Van den title = The GLEaMviz computational tool, a publicly available software to explore realistic epidemic spreading scenarios at the global scale date = 2011-02-02 keywords = GLEaMviz; model; simulation; user summary = The GLEaMviz design aims at maximizing flexibility in defining the disease compartmental model and configuring the simulation scenario; it allows the user to set a variety of parameters including: compartment-specific features, transition values, and environmental effects. GLEaMviz is a client-server software system that can model the world-wide spread of epidemics for human transmissible diseases like influenzalike illnesses (ILI), offering extensive flexibility in the design of the compartmental model and scenario setup, including computationally-optimized numerical simulations based on high-resolution global demographic and mobility data. GLEaMviz makes use of a stochastic and discrete computational scheme to model epidemic spread called "GLEaM" -GLobal Epidemic and Mobility model, presented in previously published work [6, 3, 14] which is based on a geo-referenced metapopulation approach that considers 3,362 subpopulations in 220 countries of the world, as well as air travel flow connections and short-range commuting data. doi = 10.1186/1471-2334-11-37 id = cord-186031-b1f9wtfn author = Caldarelli, Guido title = Analysis of online misinformation during the peak of the COVID-19 pandemics in Italy date = 2020-10-05 keywords = Italy; Twitter; community; italian; network; political; user summary = When analysing the emerging 4 communities, we find that they correspond to 1 Right wing parties and media (in steel blue) 2 Center left wing (dark red) 3 5 Stars Movement (M5S ), in dark orange 4 Institutional accounts (in sky blue) Details about the political situation in Italy during the period of data collection can be found in the Supplementary Material, Section 1.2: ''Italian political situation during the Covid-19 pandemics''. In line with previous results on the validated network of verified users, the table clearly shows how the vast majority of the news coming from sources considered scarce or non reputable are tweeted and retweeted by the center-right and right wing communities; 98% of the domains tagged as NR are shared by them. doi = nan id = cord-236830-0y5yisfk author = Chan, Justin title = PACT: Privacy Sensitive Protocols and Mechanisms for Mobile Contact Tracing date = 2020-04-07 keywords = positive; time; user summary = Importantly, these protocols, by default, keep all personal data on a citizens'' phones (aside for pseudonymous identifiers broadcast to other local devices), while enabling these key capabilities; information is shared via voluntary disclosure actions taken, with the understandings relayed via careful disclosure. From a civil liberties standpoint, the privacy guarantees these protocols ensure are designed to be consistent with the disclosures already extant in contract tracing methods done by public health services (where some information from a positive tested citizen is revealed to other at risk citizens). Preventing proximity-based identification of this sort is not possible to avoid in any protocol, even in manual contact tracing as done by public health services, simply because the exposure alert may contain information that is correlated with identifying information. To discuss the consequences of these properties on privacy and integrity, let us refer to users as either "positive" or "negative" depending on whether they decided to report as positive, by uploading their seed to the server, or not. doi = nan id = cord-350000-eqn3kl5p author = Drissi, Nidal title = An Analysis on Self-Management and Treatment-related Functionality and Characteristics of Highly Rated Anxiety Apps date = 2020-07-30 keywords = anxiety; app; health; mental; user summary = The objective of this study is to provide an analysis of treatment and management-related functionality and characteristics of high-rated mobile applications (apps) for anxiety, which are available for Android and iOS systems. Results also showed that 51% of the selected apps used various gamification features to motivate users to keep using them, 32% provided social features including chat, communication with others and links to sources of help; 46% offered offline availability; and only 19% reported involvement of mental health professionals in their design. This study aims to analyze the functionality and characteristics of highly 5 J o u r n a l P r e -p r o o f rated anxiety apps to identify users'' preferred features and management methods delivered for anxiety with a smartphone or a tablet. doi = 10.1016/j.ijmedinf.2020.104243 id = cord-302724-hu0raqyi author = Finazzi, Francesco title = The impact of the Covid‐19 pandemic on Italian mobility date = 2020-05-27 keywords = user summary = The impact of the Covid-19 pandemic on Italian mobility Francesco Finazzi and Alessandro Fassò use location data collected by an earthquake-monitoring app to gauge compliance with lockdown measures in Italy make some assessment of the public''s compliance with mobility restrictions during the period of maximum growth of infections and hospitalisations. In order to provide real-time detection and alerts, the app collects phone location FIGURE 1 Mobility in Italy estimated through smartphone data collected by the Earthquake Network project. Cochran explains why a misunderstanding or disregard of exponential growth may have extremely grave consequences D uring his 26 March call into The Sean Hannity Show on Fox News, President Donald Trump questioned whether New York State would actually need the tens of thousands of ventilators its leaders had estimated would be necessary to deal with its expected number of coronavirus cases (bit.ly/3bw0AyZ). doi = 10.1111/1740-9713.01400 id = cord-355789-x449xflm author = Frauenstein, Edwin Donald title = Susceptibility to phishing on social network sites: A personality information processing model date = 2020-05-01 keywords = Facebook; personality; processing; trait; user summary = Based on the literature studied, this research presents a theoretical model to address phishing susceptibility on SNSs. Using data collected from 215 respondents, the study examined the mediating role that information processing plays with regard to user susceptibility to social network phishing based on their personality traits, thereby identifying user characteristics that may be more susceptible than others to phishing on SNSs. The results from the structural equation modeling (SEM) analysis revealed that conscientious users were found to have a negative influence on heuristic processing, and are thus less susceptible to phishing on SNSs. The study also confirmed that heuristic processing increases susceptibility to phishing, thus supporting prior studies in this area. As such, this study follows this recommendation by identifying particular users susceptible to social network phishing by their personality traits, as this is one of the factors that have recently been found to influence user behaviour ( Shropshire et al., 2015 ) . doi = 10.1016/j.cose.2020.101862 id = cord-020901-aew8xr6n author = García-Durán, Alberto title = TransRev: Modeling Reviews as Translations from Users to Items date = 2020-03-17 keywords = embedding; review; user summary = TransRev learns vector representations for At training time, a function''s parameters are learned to compute the review embedding from the word token embeddings such that the embedding of the user translated by the review embedding is similar to the product embedding. Methods that fall into this category such as [31, 32] learn latent representations of users and items from the text content so as to perform well at rating prediction. Similar to sentiment analysis methods, TransRev trains a regression model that predicts the review rating from the review text. We compare to the following methods: a SVD matrix factorization; HFT, which has not often been benchmarked in previous works; and DeepCoNN [38] , which learns user and item representations from reviews via convolutional neural networks. Representation learning of users and items for review rating prediction using attention-based convolutional neural network doi = 10.1007/978-3-030-45439-5_16 id = cord-323372-770sos8m author = Glenn, Jeffrey title = Considering the Potential Health Impacts of Electric Scooters: An Analysis of User Reported Behaviors in Provo, Utah date = 2020-08-31 keywords = Electric; Provo; ride; scooter; user summary = title: Considering the Potential Health Impacts of Electric Scooters: An Analysis of User Reported Behaviors in Provo, Utah Stand-up electric scooters (e-scooters), two-wheeled vehicles with a small electric motor and a thin deck on which a single rider stands, are a relatively new micro-mobility option for urban areas and have the potential for both positive and negative health impacts [2] [3] [4] . The aim of this study is to explore the health-related behaviors of e-scooter users in Provo, Utah four months after an e-scooter share program was introduced. This finding is particularly relevant for Provo City, a place with problematic winter air pollution and whose primary motivation for introducing e-scooters was to provide a green alternative to motor vehicles; yet, considering disposability issues and emissions due to collecting and placement of e-scooters, important questions remain about the full environmental impact and its implications for health. doi = 10.3390/ijerph17176344 id = cord-032466-1nfp1hcs author = Gong, Liang title = Interaction design for multi-user virtual reality systems: An automotive case study date = 2020-09-22 keywords = system; user summary = title: Interaction design for multi-user virtual reality systems: An automotive case study It has shown that VR technologies have great advantages to improve areas like factory layout planning, product design, training, etc., especially for globally distributed manufacturing companies that have different functional team located in different parts of the world [3] , [5] [8] . In this study, we have chosen a globally distributed manufacturing company as the case to study the different possibilities of interaction design approaches for the multi-user VR system used in the design review process. In this study, we have chosen a globally distributed manufacturing company as the case to study the different possibilities of interaction design approaches for the multi-user VR system used in the design review process. In this study, we have chosen a globally distributed manufacturing company as the case to study the different possibilities of interaction design approaches for the multi-user VR system used in the design review process. doi = 10.1016/j.procir.2020.04.036 id = cord-020200-g5hy5ncm author = Grobler, Chris D. title = Towards a Strategic Model for Safeguarding the Preservation of Business Value During Human Interactions with Information Systems date = 2020-03-06 keywords = user; value summary = In adopting a slightly dystopic view, our focus in this paper is seated within the context of the potentially negative impact that end-users have on organisations when discontinuing the use of a particular mandated IS [2] , or making misuse of information within an IS that is intended to drive value realisation [3, 4] . The primary purpose is to build a value framework from which an empirically-endorsed model can be constructed, and through which the unintended business value dissipating effects on institutions, as a direct result of end-user''s misuse of IS, may be investigated and moderated. Three secondary objectives that dictate the structure of this paper are pursued: (1) to review key characteristics from several germane models and theories relating to the business impact of HCI that maps to, and refines, a rudimentary Conceptual Technology Value Framework (CTVF), (2) to apply the CTVF as a basis for a qualitative investigation from which an Adjusted Technology Value Model (ATVM) may be derived and contextualized, and (3) to present the ATVM as a first benchmark to identify, investigate, mitigate and minimise or eliminate unintentional value destroying effects. doi = 10.1007/978-3-030-44999-5_29 id = cord-000925-91fhb66m author = Hashemian, Mohammad R. title = Advanced Querying Features for Disease Surveillance Systems date = 2010-04-09 keywords = AQT; query; user summary = The objective of the Advance Querying Tool (AQT) is to build a more flexible query interface for most web-based disease surveillance systems. Our prototype system, the Advanced Querying Tool (AQT), allows the investigators to handle complex cases where one can incorporate any data elements available in a disease surveillance system, then mix and match these data elements in order to define valid queries. Table 1 provides examples of how a dynamic query tool exploits combinations of data elements available to disease surveillance systems. The following objectives summarize the design features of the AQT: The tool''s interface will help generate queries that can process any kind of data regardless of its source (e.g., emergency room visit, office visit, pharmacy, and laboratory). Making the tool adaptable to many web-based systems requires the AQT to contain all the processing dynamically, including validating the query syntax and changing the contents of the list boxes. doi = 10.5210/ojphi.v2i1.2847 id = cord-031614-l5seadro author = Heumader, Peter title = Adaptive User Interfaces for People with Cognitive Disabilities within the Easy Reading Framework date = 2020-08-12 keywords = interface; user summary = This paper describes how such user interfaces are implemented within the Easy Reading framework, a framework to improve the accessibility of web-pages for people with cognitive disabilities. MyUI on the other hand was an EU funded project that enabled the generation of individualized user interfaces that would adapt to the individual users needs in realtime, based on a user profile and the actual device [10, 12, 13] . Adaptations within the Easy Reading framework can be applied to the user interface, the help that is provided, the user interaction (how help is triggered) and finally how the help is rendered and presented within the web-page. • Input Support: Stores the preferred way to triggering help and to select where on the web-page help is needed • Output Support: Specifies the preferred way of rendering the help provided Based on these categories, once the user logs in with his or her user profile, a dynamically optimized configuration is created for the individual user (see Fig. 2 ). doi = 10.1007/978-3-030-58805-2_7 id = cord-139715-jyfmnnf5 author = Holzapfel, Kilian title = Digital Contact Tracing Service: An improved decentralized design for privacy and effectiveness date = 2020-06-29 keywords = DCTS; GDPR; Sec; section; tcn; user summary = We present a secure solution for a digital contact tracing service (DCTS) that protects the users'' privacy, identity and personal data from attackers. In order to check whether the user has been in contact with an infected person, they download all unchecked TCNs stored on the server and check for matches within their own list of observed TCNs. When encountering matches, the app can perform a risk assessment based on exposure time period and proximity. In order to avoid this attack, we can check for the number of TCNs that are both in our set of encountered TCNs and in the set of infected TCNs. An algorithm determining the private set intersection cardinality with low communication cost (see for example 3 ) is a valuable strategy in order to discover the exposure to infectious contacts without risking the identification of the patient (details are described in Section 3.6). doi = nan id = cord-031617-l9iacaec author = Iwamura, Masakazu title = Suitable Camera and Rotation Navigation for People with Visual Impairment on Looking for Something Using Object Detection Technique date = 2020-08-10 keywords = object; user summary = title: Suitable Camera and Rotation Navigation for People with Visual Impairment on Looking for Something Using Object Detection Technique For people with visual impairment, smartphone apps that use computer vision techniques to provide visual information have played important roles in supporting their daily lives. Then, in looking for something as a representative task in a category, we argue suitable camera systems and rotation navigation methods. Obtaining the visual information on the object that the user photographs Current smartphone apps that use computer vision techniques such as [6, 11, 12] can be used. In this experiment, we asked participants to use five rotation navigation methods one by one through Steps 1 (object detection using the omnidirectional camera) and 2 (rotation navigation) in Sect. A user study comprised of seven people with visual impairment confirmed that (1) a camera with a wide FoV is better in such a task, and (2) users have different preferences in rotation navigation. doi = 10.1007/978-3-030-58796-3_57 id = cord-027078-i3a5jwck author = Jiang, Bo title = Social Recommendation in Heterogeneous Evolving Relation Network date = 2020-05-26 keywords = relation; user summary = In this paper, we propose a novel social recommendation model based on evolving relation network, named SoERec. The learned evolving relation network is a heterogeneous information network, where the strength of relation between users is a sum of the influence of all historical events. -We propose a novel social recommendation model by jointly embedding representations of fine-grained relations from historical events based on heterogeneous evolving network. -We conduct several analysis experiments with two real-world social network datasets, the experimental results demonstrate our proposed model outperforms state-of-the art comparison methods. Various methods of social recommendation have been proposed from different perspectives in recent years including user-item rating matrix [15] , network structure [11] , trust relationship [5, 10, 18, 27] , individual and friends'' preferences [6, 12] , social information [25] and combinations of different features [19, 26] . In particular, we leverage the LINE model to learn users'' embedded representations of the evolving relation network the firstorder proximity and the second-order proximity. doi = 10.1007/978-3-030-50371-0_41 id = cord-120017-vsoc9v85 author = Jiang, Helen title = Usable Security for ML Systems in Mental Health: A Framework date = 2020-08-18 keywords = security; system; user summary = We aim to weave together threads from different domains, incorporate existing views, and propose new principles and requirements, in an effort to lay out a clear framework where criteria and expectations are established, and are used to make security mechanisms usable for end-users of those ML systems in mental health. In this short paper, we propose that ML systems in mental health use cases, beyond the privacy and security requirements already mandated by legislation''s and regulations -for example, Health Insurance Portability and Accountability Act (HIPPA) [38, 43, 64] in United States, and General Data Protection Regulation (GDPR) in European Union and its member states'' national laws [11, 12] -should consider properties of usable security proposed by this framework''s four pillars, and be evaluated on their (1)context models, (2)functionality criteria, (3)trustworthiness requirements, and (4)recovery principles across their life cycles. doi = nan id = cord-102542-1mglhh41 author = Jovanovi''c, Mladjan title = Chatbots as conversational healthcare services date = 2020-11-08 keywords = chatbot; healthcare; user summary = This article takes a closer look at how these emerging chatbots address design aspects relevant to healthcare service provision, emphasizing the Human-AI interaction aspects and the transparency in AI automation and decision making. This paper: • identifies salient service provision archetypes that characterize the emerging roles and functions the chatbots aim to fulfill; • assesses the design choices concerning domainspecific dimensions associated with health service provision and user experience; • provides implications for theory and practice that highlight existing gaps. The archetype does not perform the diagnosis but instead support a diagnosis by either i) facilitating access to health services, such as the Pathology Lab Chatbot facilitating access to doctors and scheduling visits, ii) supporting online consultations with health professionals, such as the iCliniq that pairs up users with doctors for online consultation, and iii) providing conversational access to information regarding symptoms and diseases, such as the WebMD. doi = 10.1109/mic.2020.3037151 id = cord-186764-qp4kq139 author = Klopfenstein, Lorenz Cuno title = Digital Ariadne: Citizen Empowerment for Epidemic Control date = 2020-04-16 keywords = Ariadne; contact; user summary = In this paper, we outline general requirements and design principles of personal applications for epidemic containment running on common smartphones, and we present a tool, called ''diAry'' or ''digital Ariadne'', based on voluntary location and Bluetooth tracking on personal devices, supporting a distributed query system that enables fully anonymous, privacy-preserving contact tracing. The proposed system allows individuals to keep track of movements and contacts on their own private devices and to use local traces to select relevant notifications and alerts from health authorities, thus completely eschewing, by design, any risk of surveillance. The system is composed of: a mobile application, that is voluntarily installed by users on their smartphones, keeping track of their locations through the device''s GPS sensor and interactions with other users through Bluetooth radio beacons, a privacy-aware reward system, which incentivizes app usage while collecting anonymous usage information to feed an open data set, and a distributed query system that allows recognized public authorities to selectively and anonymously notify users about possible contagion sources. doi = nan id = cord-027120-w6agcu63 author = Lago, André Sousa title = Conversational Interface for Managing Non-trivial Internet-of-Things Systems date = 2020-05-25 keywords = Jarvis; system; user summary = In this work we present Jarvis, a conversational interface to manage IoT systems that attempts to address these issues by allowing users to specify time-based rules, use contextual awareness for more natural interactions, provide event management and support causality queries. Another common, and sometimes complementary, alternative to visual programming, is the many conversational assistants in the market, such as Google Assistant, Alexa, Siri and Cortana, that are capable of answering natural language questions and which recently gained the ability to interact with IoT devices (see [18] and [15] for a comparison of these tools). In this paper we presented a conversational interface prototype able to carry several different management tasks currently not supported by voice assistants, with capabilities that include: (1) Delayed, periodic and repeating actions, enabling users to perform queries such as "turn on the light in 5 min" and "turn on the light every day at 8 am"; (2) The usage of contextual awareness for more natural conversations, allowing interactions that last for multiple sentences and provide a more intuitive conversation, e.g. doi = 10.1007/978-3-030-50426-7_29 id = cord-292065-3p4bf9ik author = Lai, Lucinda title = Usage Patterns of a Web-Based Palliative Care Content Platform (PalliCOVID) during the COVID-19 Pandemic date = 2020-07-27 keywords = Analytics; care; user summary = OBJECTIVE: The primary objective of this study was to evaluate usage patterns of PalliCOVID to understand user behavior in relation to this palliative care content platform during the period of the local peak of COVID-19 infection in Massachusetts. • Accurate: Content was reviewed by palliative care experts to reflect the best available scientific evidence • Practical: Recommendations were designed to be useful and implementable by nonpalliative care clinicians in a variety of care settings • Accessible: Content was presented in a format that was optimized for viewing on both mobile devices and desktop computer screens • Applicable: Content was specific to the care of patients with confirmed or suspected COVID-19 infection and took into account the need to limit face-to-face interactions due to enhanced infection control measures and restricted visitor policies The primary objective of this study was to collect and analyze usage data from PalliCOVID as a way to better understand user behavior and gain insights about the population of users accessing this palliative care content platform. doi = 10.1016/j.jpainsymman.2020.07.016 id = cord-267860-mc0xa5om author = Lam, Simon C. title = Evaluation of the user seal check on gross leakage detection of 3 different designs of N95 filtering facepiece respirators date = 2016-05-01 keywords = N95; seal; user summary = This study, hence, aimed to examine the sensitivity, specificity, predictive values, and likelihood ratios of the user seal check on actual gross leakage detection during normal breath-ing or deep breathing without head and body movement in 3 common respirator models of different designs. The results of the user seal check compared with the gold standard QNFT on actual gross leakage through cross tabulation were used to compute the following diagnostic parameters: sensitivity, specificity, positive and negative predictive values, and likelihood ratios (refer to the "NOTE" in Table 4 for the respective formula). To illustrate the clinical implication of the current results of predictive values and likelihood ratios, by using an example of donning the 3M-A respirator, an interpretative summary of the validity and test performance of the user seal check for identifying actual gross leakage is presented as follows. doi = 10.1016/j.ajic.2015.12.013 id = cord-102738-e5zojanb author = Lieberoth, Andreas title = Getting Humans to do Quantum Optimization - User Acquisition, Engagement and Early Results from the Citizen Cyberscience Game Quantum Moves date = 2015-06-26 keywords = Moves; Quantum; figure; game; level; player; user summary = Among statistical predictors for retention and in-game high scores, the data from our first year suggest that people recruited based on real-world physics interest and via real-world events, but only with an intermediate science education, are more likely to become engaged and skilled contributors. Recruitment activities in-world and online, an engaging in-game core loop, a structural gameplay to frame, structure and motivate the player''s continual progression through the levels, as well as an active community where participants get a sense of continually contributing to science, are all central components of the strategy laid out to hopefully realizing the scientific goals of Quantum Moves. While Quantum Moves is unique compared to other citizen science games in having an engaging and challenging core game loop that by itself lives up to prominent definitions of (casual) games (Juul, 2005; Salen & Zimmerman, 2004) , we also expect that a well-designed structural gameplay (sometimes called metagame) is central to frame, structure and motivate the play experience, both helping and goading players to move from level to level along appropriate learning curves balanced between boredom and anxiety. doi = 10.15346/hc.v1i2.11 id = cord-318195-38gu0yab author = Logeswaran, Abison title = The Electronic Health Record in Ophthalmology: Usability Evaluation Tools for Health Care Professionals date = 2020-10-26 keywords = EHR; UCD; user summary = In this paper, we describe practical qualitative methodologies that can be used by HCPs in the design, implementation and evaluation of ophthalmology EHRs. METHODS: A review of current qualitative usability methodologies was conducted by practising ophthalmologists who are also qualified health informaticians. The impact of COVID-19 has confirmed the necessity and usefulness of structured queries, triage and prioritization; these are elements that can potentially be addressed by well-designed EHRs. This might further drive the usage and adoption of EHRs. EHR vendors in countries such as the USA are obliged to meet certification requirements set by the Office of the National Coordinator for Health Information Technology in efforts to promote user centred design (UCD). UCD processes and usability testing methodology reports provided by vendors can be complex, making it difficult for HCPs who are not trained in usability science to understand the information. A framework for evaluating electronic health record vendor user-centered design and usability testing processes doi = 10.1007/s40123-020-00315-0 id = cord-355513-vgs96w3b author = Ma, Rongyang title = Effects of Health Information Dissemination on User Follows and Likes during COVID-19 Outbreak in China: Data and Content Analysis date = 2020-07-14 keywords = account; article; information; user summary = title: Effects of Health Information Dissemination on User Follows and Likes during COVID-19 Outbreak in China: Data and Content Analysis Results: For nonmedical institution accounts in the model, report and story types of articles had positive effects on users'' following behaviors. In this work, we aimed to determine whether and how health information dissemination affected users'' information behavior in terms of following an account and liking a post. We chose the number of different types of articles and the aggregated number of headlines on NCP posted on the selected accounts in a 7-day period as independent variables (a total of seven) to denote the health information source and reflect the dissemination state. We want to explore whether information conveyed in each type of articles posted on WeChat can play the role, impacting users'' following and liking behavior. doi = 10.3390/ijerph17145081 id = cord-238444-v9gfh3m1 author = Maghdid, Halgurd S. title = A Smartphone enabled Approach to Manage COVID-19 Lockdown and Economic Crisis date = 2020-04-25 keywords = COVID-19; contact; user summary = Further, authorities use case quarantine strategy and manual second/third contact-tracing to contain the COVID-19 disease. In this paper, we developed a smartphone-based approach to automatically and widely trace the contacts for confirmed COVID-19 cases. From a technical standpoint, we summarise the most important contributions of this paper as follows: 1) We build a tracking model based on positional information of registered users to conduct contact-tracing of confirmed COVID-19 cases. The best thing to do seems to be let people go out for their business, but any body tests positive of COVID-19, we would be able, through proposed framework, to trace everybody in contact with the confirmed case and managing the lockdown and mass quarantine. In this study, K-means as an unsupervised machine learning algorithm is used to cluster the users'' positions information and predict that the area should be locked down or not based on same empirical thresholds. doi = nan id = cord-269850-5pidolqb author = Maghdid, Halgurd S. title = A Smartphone Enabled Approach to Manage COVID-19 Lockdown and Economic Crisis date = 2020-08-14 keywords = COVID-19; contact; user summary = 1. We build a tracking model based on positional information of registered users to conduct contact-tracing of confirmed COVID-19 cases. The best thing to do seems to be let people go out for their business, but any body tests positive of COVID-19, we would be able, through proposed framework, to trace Fig. 3 A framework of contact-tracing using smartphone-based approach everybody in contact with the confirmed case and managing the lockdown and mass quarantine. In this study, k-means as an unsupervised machine learning algorithm is used to cluster the users'' positions information and predict that the area should be locked down or not based on the same empirical thresholds. This Fig. 6 The results of the prediction model for both scenarios is followed by send back notifications from the server to the users to notify them for the crowded area and controlling the spreading the coronavirus COVID-19. doi = 10.1007/s42979-020-00290-0 id = cord-156676-wes5my9e author = Masud, Sarah title = Hate is the New Infodemic: A Topic-aware Modeling of Hate Speech Diffusion on Twitter date = 2020-10-09 keywords = Twitter; hate; model; retina; user summary = For predicting the initiation of hate speech for any given hashtag, we propose multiple feature-rich models, with the best performing one achieving a macro F1 score of 0.65. For both detecting and predicting the spread of hate speech over short tweets, the knowledge of context is likely to play a decisive role Present work: Based on the findings of the existing literature and the analysis we presented above, here we attempt to model the dynamics of hate speech spread on Twitter. 1) We formalize the dynamics of hate generation and retweet spread on Twitter subsuming, the activity history of each user and signals propagated by the localized structural properties of the information network of Twit-ter induced by follower connections as well as global endogenous and exogenous signals (events happening inside and outside of Twitter) (See Section III). Features representing hateful behavior encoded within the given tweet as well as the activity history of the users further help RETINA to achieve a macro F1-score of 0.85, significantly outperforming several state-of-the-art retweet prediction models. doi = nan id = cord-120498-b1bla3fp author = McFate, Clifton title = SKATE: A Natural Language Interface for Encoding Structured Knowledge date = 2020-10-20 keywords = SKATE; frame; user summary = In this paper we describe how our approach, called SKATE, uses a neural semantic parser to parse NL input and suggest semi-structured templates, which are recursively filled to produce fully structured interpretations. We demonstrate how SKATE has been integrated with a natural language rule generation model to interactively acquire structured rules for story understanding, and conclude with a current application that uses SKATE to build COVID-19 policy diagrams. For example, in the second pane of Figure 2 , the template generator has built frame assignment options for the word "take." The resulting micro-dialogue is presented to the user. SKATE''s performance improves with annotated examples, but they are not required, and as discussed in the next subsection, SKATE can generate its own training data as a new frame is selected by the user and elaborated upon in SKATE interactions. Our approach leverages recent advances in language modeling to generate templates from user text and to provide unstructured guidance. doi = nan id = cord-024433-b4vw5r0o author = Morales, Alex title = CrowdQM: Learning Aspect-Level User Reliability and Comment Trustworthiness in Discussion Forums date = 2020-04-17 keywords = comment; post; user summary = title: CrowdQM: Learning Aspect-Level User Reliability and Comment Trustworthiness in Discussion Forums CrowdQM addresses these limitations by modeling the fine-grained aspect-level reliability of users and incorporate semantic similarity between words to learn a latent trustworthy comment embedding. CrowdQM addresses both limitations by jointly modeling the aspect-level user reliability and latent trustworthy comment in an optimization framework. The update of the embeddings depend on the submission context v c , latent trustworthy comment embedding, a * m as well as user-post reliability score, R m,n . Note that both approaches do not model aspect-level user reliability but use semantic representations of comments. To the best of our knowledge, there has been no work that models both fine-grained user reliability with semantic representations of the text to discover trustworthy comments from community responses. We proposed an unsupervised model to learn a trustworthy comment embedding from all the given comments for each post in a discussion forum. doi = 10.1007/978-3-030-47426-3_46 id = cord-027431-6twmcitu author = Mukhina, Ksenia title = Spatiotemporal Filtering Pipeline for Efficient Social Networks Data Processing Algorithms date = 2020-05-25 keywords = Twitter; datum; location; user summary = To do that we propose a spatiotemporal data processing pipeline that is general enough to fit most of the problems related to working with LBSNs. The proposed pipeline includes four main stages: an identification of suspicious profiles, a background extraction, a spatial context extraction, and a fake transitions detection. Efficiency of the pipeline is demonstrated on three practical applications using different LBSN: touristic itinerary generation using Facebook locations, sentiment analysis of an area with the help of Twitter and VK.com, and multiscale events detection from Instagram posts. Thus, all studies based on social networks as a data source face two significant issues: wrong location information stored in the service (wrong coordinates, incorrect titles, duplicates, etc.) and false information provided by users (to hide an actual position or to promote their content). doi = 10.1007/978-3-030-50433-5_7 id = cord-031616-dckqb6er author = Murillo-Morales, Tomas title = Automatic Assistance to Cognitive Disabled Web Users via Reinforcement Learning on the Browser date = 2020-08-12 keywords = Easy; Reading; user summary = It aims to infer the user''s current cognitive state by collecting and analyzing user''s physiological data in real time, such as eye tracking, heart beat rate and variability, and blink rate. These tools embed alternative easy-to-read or clarified content directly into the original Web document being visited when the user requests it, thereby enabling persons with a cognitive disability to independently browse the Web. Access methods may be tailored to the specific users based on personal data, generally created by supporting staff or educators [8] . The main advantage of the Easy Reading framework over existing cognitive support methods is that the personalized support tools are provided at the original websites in an automatic fashion instead of depending on separate user experiences which are commonly provided to users in a static, content-dependent manner and that must be manually authored by experts. The Easy Reading Reasoner is the client-based module in charge of solving the problem of inferring the affective state of the user from the current readings of physiological signals collected by a running AsTeRICS model. doi = 10.1007/978-3-030-58805-2_8 id = cord-201675-3bvshhtn author = Ng, Pai Chet title = COVID-19 and Your Smartphone: BLE-based Smart Contact Tracing date = 2020-05-28 keywords = Fig; RSS; smartphone; user summary = The proposed Smart Contact Tracing (SCT) system utilizes the smartphones Bluetooth Low Energy (BLE) signals and machine learning classifier to accurately and quickly determined the contact profile. The proposed Smart Contact Tracing (SCT) system utilizes the smartphones Bluetooth Low Energy (BLE) signals and machine learning classifier to accurately and quickly determined the contact profile. • Privacy-preserving signature protocol: our SCT system provides a secure contact tracing by using the nonconnectable advertising channels and an encrypted packet containing unique signature information based on the ambient environmental features observed by a smartphone. To bridge the gap, this paper studies the proximity sensing with the BLE signals broadcast from the smartphones carried by the user while designing a privacypreserving signature protocol that uses the environmental feature instead of user information for packet broadcasting. Besides signature matching, the application also performs the classification to classify the potential risk of a user according to the time and distance the user spent with the infected individual. doi = nan id = cord-124191-38i44n0m author = Okoshi, Tadashi title = NationalMood: Large-scale Estimation of People''s Mood from Web Search Query and Mobile Sensor Data date = 2020-11-02 keywords = SMM; mood; score; user summary = Our large-scale data analysis with about 11,000,000 users and 100 recent advertisement log revealed (1) the existence of certain class of advertisement to which mood-status-based delivery would be significantly effective, (2) that our"National Mood Score"shows the ups and downs of people''s moods in COVID-19 pandemic that inversely correlated to the number of patients, as well as the weekly mood rhythm of people. In this paper, as the first contribution, we show that we can estimate the web users'' affective status (concretely, "mood") in such a condition, based on a novel combinational use of their web search queries and mobile sensor data. Then, by combining the web search logs of the 460 participants during the study period and mood status (based on both the users'' original annotation and SMM''s outputs), we create our second model "QMM", which estimates the mood of a user from their search query data. doi = nan id = cord-020820-cbikq0v0 author = Papadakos, Panagiotis title = Dualism in Topical Relevance date = 2020-03-24 keywords = query; user summary = To this end, in this paper we elaborate on the idea of leveraging the available antonyms of the original query terms for eventually producing an answer which provides a better overview of the related conceptual and information space. In this paper we elaborate on the idea of leveraging the available antonyms of the original query terms (if they exist), for eventually producing an answer which provides a better overview of the related information and conceptual space. In their comments for these queries, users mention that the selected (i.e., dual) list "provides a more general picture" and "more relevant and interesting results, although contradicting". For the future, we plan to define the appropriate antonyms selection algorithms and relevance metrics, implement the proposed functionality in a meta-search setting, and conduct a large scale evaluation with real users over exploratory tasks, to identify in which queries the dual approach is beneficial and to what types of users. doi = 10.1007/978-3-030-45442-5_40 id = cord-122159-sp6o6h31 author = Raskar, Ramesh title = COVID-19 Contact-Tracing Mobile Apps: Evaluation and Assessment for Decision Makers date = 2020-06-04 keywords = COVID-19; app; contact; user summary = By comparing the device users'' location trails or the anonymous ID tokens they have collected with those from people who have COVID-19, one can identify others who have been near the person who is infected; this facilitates contact tracing in a more accurate and timely manner than the traditional manual approach. • An authority (public health official, healthcare provider, government official) collects the location history from the person who is infected and makes it available to users of the app. For this reason, we are building not only a contact-tracing app, but also Safe Places, a web-based tool for public health officials working to contain the COVID-19 pandemic. • Fostering trust • Developing key partnerships, including with community officials who can help drive local support for the solution • Creating solutions that meet the needs of public health officials responding to the pandemic • Focusing on the needs of the users • Providing value to the user during a contact-tracing interview even if they choose not to download the app before they have been diagnosed with COVID-19 doi = nan id = cord-227492-st2ebdah author = Raskar, Ramesh title = Apps Gone Rogue: Maintaining Personal Privacy in an Epidemic date = 2020-03-19 keywords = carrier; contact; user summary = • Users are individuals who have not been diagnosed with an infectious disease who seek to use a contact-tracing tool to better understand their exposure history and risk for disease. • Finally, we broadly speak of the government as the entity which makes location data public and informs those individuals who were likely in close contact with a diagnosed carrier, acknowledging that this responsibility is carried out by a different central actor in every continent, country or local region. The primary challenge for these technologies, as evident from their deployment in the COVID-19 crisis, remains securing the privacy of individuals, diagnosed carriers of a pathogen, and local businesses visited by diagnosed carriers, while still informing users of potential contacts. All containment strategies require analysis of diagnosed carrier location trails in order to identify other individuals at risk for infection. doi = nan id = cord-020936-k1upc1xu author = Sanz-Cruzado, Javier title = Axiomatic Analysis of Contact Recommendation Methods in Social Networks: An IR Perspective date = 2020-03-17 keywords = BM25; user summary = Recently, it has been shown that classical information retrieval (IR) weighting models – such as BM25 – can be adapted to effectively recommend new social contacts to a given user. In this paper, we analyze the reasons behind the effectiveness of IR approaches for the task of recommending contacts in social networks, through an exploratory analysis of the importance and validity of the fundamental IR axioms [13] . Interestingly, we find that while this is generally true, the axioms related to length normalization negatively impact the contact recommendation performance, since they interfere with a key evolutionary principle in social networks, namely preferential attachment [8] . 3. As the only difference between the original and the version of BM25 defined by Sanz-Cruzado and Castells is just the definition of the candidate length, it is straightforward to prove that all edge weight constraints and NDC are satisfied in the same way as they are for textual IR: NDC is unconditionally true, whereas all EWC axioms depend just on the condition: doi = 10.1007/978-3-030-45439-5_12 id = cord-128041-vmmme94y author = Shen, Meng title = Bluetooth-based COVID-19 Proximity Tracing Proposals: An Overview date = 2020-08-28 keywords = Bluetooth; proposal; user summary = Then, we summarized eight security and privacy design goals for Bluetooth-based COVID-19 proximity tracing proposals and applied them to analyze the five proposals. In the centralized proximity tracing proposals, users broadcast and receive encounter information (anonymous ID, transmission time, etc.) via Bluetooth. In the decentralized proximity tracing proposals, when users are infected with COVID-19, the keys related to the generation of anonymous IDs is uploaded to the server. The two decentralized proposals have roughly similar processes, and the specific difference is reflected in the different algorithms for generating anonymous IDs. In the low-cost design, the seed keys of one user are linkable. But attackers cannot obtain valid information by analyzing these messages due to using the generation algorithm of anonymous IDs. In decentralized proposals, only users who may be at risk of infection can do risk calculation. In the centralized proposals, the server handles user pseudonyms, anonymous IDs generated based on the user pseudonyms and encounter information uploaded. doi = nan id = cord-035285-dx5bbeqm author = Simmhan, Yogesh title = GoCoronaGo: Privacy Respecting Contact Tracing for COVID-19 Management date = 2020-11-11 keywords = App; Bluetooth; COVID-19; GCG; contact; user summary = This proximity data of all app users are used to build a temporal contact graph, where vertices are devices, and edges indicate proximity between devices for a certain time period and with a certain Bluetooth signal strength. The use of the GCG App within an institutional setting, with data collection and usage governed by the organization, may lead to higher adoption of the app and enhance its effectiveness in contact tracing. The use of GCG is strictly voluntary, and there is an additional consent required by a user who is infected with COVID-19 before their data can be used for contact tracing-this, despite their data already being available centrally in the backend. Besides tracking Bluetooth contact data, the GCG App offers several features to inform the users about COVID-19 and engage them in preventing its spread. doi = 10.1007/s41745-020-00201-5 id = cord-223669-hs5pfg4b author = Song, Jinyue title = Blockchain Meets COVID-19: A Framework for Contact Information Sharing and Risk Notification System date = 2020-07-20 keywords = Bluetooth; Contract; system; user summary = The proposed system unifies location-based and Bluetooth-based contact tracing services into the Blockchain platform, where the automatically executed smart contracts are deployed so that users can get consistent and non-tamperable virus trails. This system implements the following main functions with smart contracts and Bluetooth embedded: (1) Users can record their visited location information and personal contact history to the blockchain database. • We propose an optimal equation for the operating costs of the system, simulate person-to-person contact and user check-in activities in our system, and evaluate the system performance based on the different quantity of users and smart contracts. In our system, three main technologies guarantee data security and personal privacy: decentralized database in the blockchain, automatic execution of smart contracts, and randomization of Bluetooth mac addresses. In our system, the blockchain database will store all transactions in the network, including users'' Bluetooth contact records, check-in information of the visited locations, and the change of the user''s public health status. doi = nan id = cord-130143-cqkpi32z author = Tajan, Louis title = Approach for GDPR Compliant Detection of COVID-19 Infection Chains date = 2020-07-16 keywords = Bloom; user summary = While prospect of tracking mobile devices'' users is widely discussed all over European countries to counteract COVID-19 propagation, we propose a Bloom filter based construction providing users'' location privacy and preventing mass surveillance. We apply a solution based on Bloom filters data structure that allows a third party, a government agency, to perform some privacy-preserving set relations on a mobile telco''s access logfile. By computing set relations, the government agency, given the knowledge of two identified persons, has an instrument that provides a (possible) infection chain from the initial to the final infected user no matter at which location on a worldwide scale they are. Even if this regulation does not apply on fields as public health or national security [5] , weaving the proposed Bloom filter based private protocols into infection chains investigation would limit government agencies to solely identify users with high probability of being infected instead of a massive data analysis of all mobile users. doi = nan id = cord-251676-m8f6de33 author = Trivedi, Amee title = WiFiTrace: Network-based Contact Tracing for Infectious Diseases Using Passive WiFi Sensing date = 2020-05-25 keywords = contact; location; user summary = The tool analyses WiFi logs generated by the network, and specifically association and dissociation log messages for this device, at various access points on campus to reconstruct the location(building, room numbers) visited by the user. We note that such a client-centric approach requires a user to first download a mobile app before contact tracing data can be gathered-users who have not downloaded the app (or have opted in) are not visible to other phones that are actively listening for other devices in their proximity. As discussed below, this tier uses time-evolving graphs and efficient graph algorithms to efficiently intersect trajectories of a large number of devices (typically tens of thousands of users that may be present on a university campus) to produce its report. In this section, we describe case studies that evaluate the efficacy of our contact tracing tool and also present results on the efficiency of our graph algorithms and general limitations of our WiFi sensing approach. doi = nan id = cord-033725-rlzbznav author = Unnikrishnan, Vishnu title = Predicting the Health Condition of mHealth App Users with Large Differences in the Number of Recorded Observations - Where to Learn from? date = 2020-09-19 keywords = user summary = title: Predicting the Health Condition of mHealth App Users with Large Differences in the Number of Recorded Observations Where to Learn from? We propose an approach that learns from users who contribute long sequences of inputs to predict the subjective perception of wellbeing for users who contribute only short sequences of input data, including users that have very recently joined the platform. -RQ2: Can we predict the entire sequence of observations of a user in U short with a model trained only on data from users in U long ? (i.e, does a model learned on data from users with long sequences transfer to those with short ones?) -RQ3: How can we incorporate early recordings of users in U short incrementally into the model to improve predictive performance? However, it is still possible that a model learned on those data points from long users bring a modest predictability to the disease development of users in U short . doi = 10.1007/978-3-030-61527-7_43 id = cord-024430-r0gbw5j6 author = Wang, Hao title = Modeling Users’ Multifaceted Interest Correlation for Social Recommendation date = 2020-04-17 keywords = correlation; user summary = Many methods have been proposed for social recommendation in recent years, and these methods can be mainly grouped into two categories: (1) memory-based methods [1, 12, 14] use social relation as an indicator that filters relevant users and directly recommend friends'' visited items to a user; (2) model-based methods [4, 5, 9, 10, 22, 27, 29, 31] integrate social relation into factorization methods to constrain that friends share similar interest embeddings. We propose to use a correlation vector, instead of a scalar value, to characterize the interest correlation between each pair of friends, and design a dimension-wise attention mechanism with the social network as input to learn it. To accommodate our problem, we further design a dimension-wise attention mechanism and use it to learn a correlation vector for each pair of friends, building their multi-dimensional interest correlation for social recommendation. doi = 10.1007/978-3-030-47426-3_10 id = cord-347144-rj76i40v author = Wang, Jiexiang title = Closed or open platform? The nature of platform and a qualitative comparative analysis of the performance effect of platform openness date = 2020-09-23 keywords = demand; openness; platform; user summary = Through decomposing platform openness into supply-side openness and demand-side openness, as well as introducing demand diversity and knowledge complexity as contextual variables, this study attempts to understand the impact of both types of attributes on performance by considering their configuration. Using fuzzy sets qualitative comparative analysis (fsQCA) method, we find that high demand diversity of platform users and high supply-side openness will lead to better platform performance. To address the causal complexity issue, this study examines the configuration effects of openness dimensions, demand diversity and knowledge complexity on platform performance using fuzzy sets qualitative comparative analysis method (QCA), a widely used method in configuration analysis (Jenson et al, 2016) . The configuration of high knowledge complexity of platform innovation with high levels of supply-side and demand-side openness will lead to high platform performance. In addition, high knowledge complexity required for platform innovation together with high supply-side and demand-side openness will contribute to a high level of platform performance. doi = 10.1016/j.elerap.2020.101007 id = cord-237721-rhcvsqtk author = Welch, Charles title = Expressive Interviewing: A Conversational System for Coping with COVID-19 date = 2020-07-07 keywords = interviewing; system; user summary = In addition, we conduct a comparative evaluation with a general purpose dialogue system for mental health that shows our system potential in helping users to cope with COVID-19 issues. 1 Research in Expressive Writing (Pennebaker, 1997b) and Motivational Interviewing (Miller and Rollnick, 2012) has shown that even simple interactions where people talk about one particular experience can have significant psychological value. In order to provide reflective feedback, the system automatically detects the topics being discussed (e.g., work, family) or emotions being felt (e.g., anger, anxiety), and responds with a reflective prompt that asks the user to elaborate or to answer a related question to explore that concept more deeply. Nonetheless, we believe that this comparison provides evidence that a dialogue system such as Expressive Interviewing is more effective in helping users cope with COVID-19 issues as compared to a general purpose dialogue system for mental health. doi = nan id = cord-027346-ldfgi0vr author = Wen, Jie title = GCN-IA: User Profile Based on Graph Convolutional Network with Implicit Association Labels date = 2020-05-22 keywords = GCN; user summary = title: GCN-IA: User Profile Based on Graph Convolutional Network with Implicit Association Labels Current researches on multi-label user profile either ignore the implicit associations among labels or do not consider the user and label semantic information in the social networks. In this paper, a graph convolutional network with implicit associations (GCN-IA) method is proposed to obtain user profile. As a result, label propagation user profile methods [4] [5] [6] are widely studied, which mainly use the social network information rather than user''s activities. To take advantage of this insight, a graph convolutional networks with implicit label associations (GCN-IA) is proposed to get user profile. A graph convolutional networks with implicit label associations (GCN-IA) method is proposed to get user profile. We first construct the social network graph with the relationship between users and design a probability matrix to record the implicit label associations, and then combine this probability matrix with the classical GCN method to embed user and label semantic information. doi = 10.1007/978-3-030-50420-5_26 id = cord-218383-t2lwqrpb author = Whaiduzzaman, Md title = A Privacy-preserving Mobile and Fog Computing Framework to Trace and Prevent COVID-19 Community Transmission date = 2020-06-23 keywords = RUERC; SUDUN; privacy; user summary = To address this problem, we develop an e-government Privacy Preserving Mobile and Fog computing framework entitled PPMF that can trace infected and suspected cases nationwide. We use personal mobile devices with contact tracing app and two types of stationary fog nodes, named Automatic Risk Checkers (ARC) and Suspected User Data Uploader Node (SUDUN), to trace community transmission alongside maintaining user data privacy. However, to the best of our knowledge, there is no integrated fog computing framework alongside contact tracing mobile apps that allows tracing community transmission while preserving users'' data privacy. However, most of these applications and frameworks have failed to ensure user data privacy and suffer from other issues, such as mandatory use of apps, excessive data gathering, questionable transparency of source codes and data flow, unnecessary data usage or processing, and lack of user control in data deletion. Our proposed privacy-preserving e-government framework has four major components: user mobile device and two types of fog nodes (ARC and SUDUN), and a central cloud application that integrates these nodes. doi = nan id = cord-020891-lt3m8h41 author = Witschel, Hans Friedrich title = KvGR: A Graph-Based Interface for Explorative Sequential Question Answering on Heterogeneous Information Sources date = 2020-03-17 keywords = graph; question; user summary = It supports both the user and the system in keeping track of the context/current focus of the search via a novel interaction concept that combines pointing/clicking and asking questions in natural language, described in Sect. In order to support them in grasping relationships between new concepts in the -often very complex -answers to their fuzzy questions, IR researchers have proposed result set visualisations that provide a better overview than the typical ranked lists of document references [1, 20] . Our contribution consists mainly in proposing a new interaction paradigm which allows users to ask questions in natural language and to receive answers in the form of visualised subgraphs of a knowledge graph. In this work, we have proposed a novel context-aware sequential question answering system, especially suited for exploratory search, based on graph visualisation for result presentation and iterative refinement of information needs. doi = 10.1007/978-3-030-45439-5_50 id = cord-310272-utqyuy0n author = Zamani, Efpraxia D. title = Appropriating Information Technology Artefacts through Trial and Error: The Case of the Tablet date = 2020-09-18 keywords = appropriation; device; error; iPad; tablet; trial; user summary = In this study we examine the use of IT artefacts following negative disconfirmation and use Grounded Theory Method techniques to analyse 136 blogposts, collected between March 2011 – July 2017, to investigate how users appropriate or reject the tablet when technology falls short of users'' expectations. The use of GTM allowed us to identify negative disconfirmation as a fairly relevant conceptual category for our study, and where appropriation and rejection are outcomes of a trial and error process where the user tries out different things in order to identify solutions to this negative disconfirmation. Users reject the tablet because they cannot overcome negative disconfirmation: they continue comparing the new to the old way of completing tasks, and they either deem the tentative solutions as not good enough or the errors as non-tolerable. The following vignettes illustrate trial and error behaviour, where iPad users try out different tentative solutions with the aim to tackle their initial negative disconfirmation. doi = 10.1007/s10796-020-10067-8 id = cord-193856-6vs16mq3 author = Zhou, Tongxin title = Spoiled for Choice? Personalized Recommendation for Healthcare Decisions: A Multi-Armed Bandit Approach date = 2020-09-13 keywords = MAB; challenge; health; model; recommendation; user summary = The first component is a deep-learning-based feature engineering procedure, which is designed to learn crucial recommendation contexts in regard to users'' sequential health histories, health-management experiences, preferences, and intrinsic attributes of healthcare interventions. Our evaluation results suggest that each of our proposed model components is effective and that our recommendation framework significantly outperforms a wide range of benchmark models, including UCB, e -greedy, and state-of-the-art conventional recommendation systems, such as context-aware collaborative filtering (CACF), probabilistic matrix factorization (PMF), and content-based filtering (CB). These research gaps motivate us to propose an online-learning scheme, i.e., multi-armed bandit (MAB), to address the dynamics and diversity in individuals'' health behaviors to improve healthcare recommendations. To better adapt an MAB to the healthcare recommendation setting, we then further enhance our framework by synthesizing two model components, that is, deep-learning-based feature engineering and a diversity constraint. To improve the characterization of individuals'' health-management contexts and enhance recommendation personalization, we design a deep-learning model to construct user embeddings. doi = nan id = cord-121200-2qys8j4u author = Zogan, Hamad title = Depression Detection with Multi-Modalities Using a Hybrid Deep Learning Model on Social Media date = 2020-07-03 keywords = CNN; Twitter; feature; model; user summary = While many previous works have largely studied the problem on a small-scale by assuming uni-modality of data which may not give us faithful results, we propose a novel scalable hybrid model that combines Bidirectional Gated Recurrent Units (BiGRUs) and Convolutional Neural Networks to detect depressed users on social media such as Twitter-based on multi-modal features. To be specific, this work aims to develop a new novel deep learning-based solution for improving depression detection by utilizing multi-modal features from diverse behaviour of the depressed user in social media. To this end, we propose a hybrid model comprising Bidirectional Gated Recurrent Unit (BiGRU) and Conventional Neural network (CNN) model to boost the classification of depressed users using multi-modal features and word embedding features. The most closely related recent work to ours is [23] where the authors propose a CNN-based deep learning model to classify Twitter users based on depression using multi-modal features. doi = nan