id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-024433-b4vw5r0o	Morales, Alex	CrowdQM: Learning Aspect-Level User Reliability and Comment Trustworthiness in Discussion Forums	2020-04-17		.txt	text/plain	4534	290	54	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.	./cache/cord-024433-b4vw5r0o.txt	./txt/cord-024433-b4vw5r0o.txt