id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-171660-iqgi1906	Yin, Hui	Detecting Topic and Sentiment Dynamics Due to COVID-19 Pandemic Using Social Media	2020-07-05		.txt	text/plain	3440	191	56	In this work, we propose a novel framework to analyze the topic and sentiment dynamics due to COVID-19 from the massive social media posts. Based on a collection of 13 million tweets related to COVID-19 over two weeks, we found that the positive sentiment shows higher ratio than the negative sentiment during the study period. Such massive personal posts from social media could become invaluable data sources for large-scale sentiment and topic mining for monitoring people's mental health across different events or topics [21] . With the spreading of COVID-19 across the world, researchers have proposed to use sentiment analysis based on social media as a tool to monitor people's mental health. [15] adopted a classic Latent Dirichlet Allocation (LDA) topic model method to generate 10 topics in a random sample of 18,000 tweets about coronavirus, then they used NRC sentiment dictionary to calculate the presence of eight different emotions, which were "anger", "anticipation", "disgust", "fear", "joy", "sadness", "surprise" and "trust".	./cache/cord-171660-iqgi1906.txt	./txt/cord-171660-iqgi1906.txt