id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_n4uw6vwblfdcpfokkebmfw6sxe	Yi Yang	Overcoming Language Variation in Sentiment Analysis with Social Attention	2017	14	.pdf	application/pdf	7498	706	58	Overcoming Language Variation in Sentiment Analysis with Social Attention novel attention-based neural network architecture, in which attention is divided among several basis models, depending on the author's could in principle be applied to any language processing task where author network information is We apply SOCIAL ATTENTION to Twitter sentiment classification, gathering social network metadata for Twitter users in the SemEval Twitter sentiment analysis tasks (Nakov et al., 2013). social networks to train user embeddings. Convolutional neural network (CNN) has been described in § 4.2, and is the basis model of SOCIAL where we report results obtained from author embeddings trained on RETWEET+ network for SOCIAL ATTENTION. With the incorporation of author social network information, concatenation slightly improves Table 5: Top 5 more positive/negative words for the basis models in the SemEval training data. As shown in Table 5, Twitter users corresponding to basis models 1 and 4 often use some words	./cache/work_n4uw6vwblfdcpfokkebmfw6sxe.pdf	./txt/work_n4uw6vwblfdcpfokkebmfw6sxe.txt