id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_7ykhqv6jm5hknnrgz2wetbzl3m	Juan Carlos Pereira-Kohatsu	Detecting and Monitoring Hate Speech in Twitter	2019	37	.pdf	application/pdf	17968	1722	63	approaches based on different document representation strategies and text classification models. tweet's word, emoji, and expression tokens' embeddings enriched by the tf-idf, and obtains an area Keywords: hate crime; sentiment analysis; text classification; predictive policing; social network can use HaterNet to analyze the evolution of different hate trends, key words, or actors; study their In our case, we design and implement a sentiment analysis model to identify tweets that contain learning approach consists of a word embedding model and a neural network ML algorithm combined HaterNet's first module, Hate Speech Detection, periodically collects tweets and classifies them as analysis suggests that, in the context of hate speech detection in Twitter, embedding-based When a new tweet is obtained for analysis, first it has to be processed by the Hate Speech Detection novel text classification model to detect hate speech and a social network analysis module to monitor	./cache/work_7ykhqv6jm5hknnrgz2wetbzl3m.pdf	./txt/work_7ykhqv6jm5hknnrgz2wetbzl3m.txt