The role of idioms in sentiment analysis. Issue 21 (30th November 2015)

• Record Type: Journal Article
• Authors: Williams, Lowri; Bannister, Christian; Arribas-Ayllon, Michael; Preece, Alun; Spasić, Irena
• Is Part Of: Expert systems with applications. Volume 42:Issue 21(2015)
• Page Start: 7375
• Page End: 7385
• Publication Date: 2015-11-30
• Subjects: Emotion recognition -- Sentiment analysis -- Natural language processing -- User-generated content -- Tagging; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2015.05.039
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: Idiom-based features significantly improve sentiment classification results. This study provides resources that can support further research into sentiment analysis. A comprehensive collection of 580 idioms annotated with sentiment polarity. A set of local grammars that can be used to recognize occurrences of these idioms. A corpus of 2521 annotated sentences in which idioms are used in context. Abstract: In this paper we investigate the role of idioms in automated approaches to sentiment analysis. To estimate the degree to which the inclusion of idioms as features may potentially improve the results of traditional sentiment analysis, we compared our results to two such methods. First, to support idioms as features we collected a set of 580 idioms that are relevant to sentiment analysis, i.e. the ones that can be mapped to an emotion. These mappings were then obtained using a web-based crowdsourcing approach. The quality of the crowdsourced information is demonstrated with high agreement among five independent annotators calculated using Krippendorff's alpha coefficient ( α = 0.662). Second, to evaluate the results of sentiment analysis, we assembled a corpus of sentences in which idioms are used in context. Each sentence was annotated with an emotion, which formed the basis for the gold standard used for the comparison against two baseline methods. The performance was evaluated in terms of three measures – precision, recall and F -measure. Overall, our approach achieved 64% and 61% for these three measures in two experiments improving the baseline results by 20 and 15 percent points respectively. F -measure was significantly improved over all three sentiment polarity classes: Positive, Negative and Other. Most notable improvement was recorded in classification of positive sentiments, where recall was improved by 45 percent points in both experiments without compromising the precision. The statistical significance of these improvements was confirmed by McNemar's test.