TDParse: Multi-target-specific sentiment recognition on Twitter

Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 483–493, Valencia, Spain, April 3-7, 2017. c⃝2017 Association for Computational Linguistics TDParse: Multi-target-specific sentiment recognition on Twitter Bo Wang Maria Liakata Arkaitz Zubiaga Rob Procter Department of Computer Science University of Warwick Coventry, UK {bo.wang, m.liakata, a.zubiaga}@warwick.ac.uk Abstract Existing target-specific sentiment recogni- tion methods consider only a single tar- get per tweet, and have been shown to miss nearly half of the actual targets men- tioned. We present a corpus of UK elec- tion tweets, with an average of 3.09 enti- ties per tweet and more than one type of sentiment in half of the tweets. This re- quires a method for multi-target specific sentiment recognition, which we develop by using the context around a target as well as syntactic dependencies involving the target. We present results of our method on both a benchmark corpus of single tar- gets and the multi-target election corpus, showing state-of-the art performance in both corpora and outperforming previous approaches to multi-target sentiment task as well as deep learning models for single- target sentiment. 1 Introduction Recent years have seen increasing interest in min- ing Twitter to assess public opinion on political affairs and controversial issues (Tumasjan et al., May 2010; Wang et al., 2012) as well as products and brands (Pak and Paroubek, 2010). Opinion mining from Twitter is usually achieved by deter- mining the overall sentiment expressed in an entire tweet. However, inferring the sentiment towards specific targets (e.g. people or organisations) is severely limited by such an approach since a tweet may contain different types of sentiment expressed towards each of the targets mentioned. An early study by Jiang et al. (2011) showed that 40% of classification errors are caused by using tweet- level approaches that are independent of the target. Consider the tweet: “I will b voting 4 Greens ... 1st reason: 2 remove 2 party alt. of labour or con- servative every 5 years. 2nd: fracking” The overall sentiment is positive but there is a negative sentiment towards “labour”, “conserva- tive” and “fracking” and a positive sentiment to- wards “Greens”. Examples like this are common in tweets discussing topics like politics. As has been demonstrated by the failure of election polls in both referenda and general elections (Burnap et al., 2016), it is important to understand not only the overall mood of the electorate, but also to dis- tinguish and identify sentiment towards different key issues and entities, many of which are dis- cussed on social media on the run up to elections. Recent developments on target-specific Twit- ter sentiment classification have explored differ- ent ways of modelling the association between tar- get entities and their contexts. Jiang et al. (2011) propose a rule-based approach that utilises de- pendency parsing and contextual tweets. Dong et al. (2014), Tang et al. (2016a) and Zhang et al. (2016) have studied the use of different recur- rent neural network models for such a …

Content truncated to 500 words