Leveraging Cognitive Features for Sentiment Analysis

Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL), pages 156–166, Berlin, Germany, August 7-12, 2016. c⃝2016 Association for Computational Linguistics Leveraging Cognitive Features for Sentiment Analysis Abhijit Mishra†, Diptesh Kanojia†,♣, Seema Nagar ⋆, Kuntal Dey⋆, Pushpak Bhattacharyya† †Indian Institute of Technology Bombay, India ♣IITB-Monash Research Academy, India ⋆IBM Research, India †{abhijitmishra, diptesh, pb}@cse.iitb.ac.in ⋆{senagar3, kuntadey}@in.ibm.com Abstract Sentiments expressed in user-generated short text and sentences are nuanced by subtleties at lexical, syntactic, semantic and pragmatic levels. To address this, we propose to augment traditional features used for sentiment analysis and sarcasm detection, with cognitive features derived from the eye-movement patterns of read- ers. Statistical classification using our en- hanced feature set improves the perfor- mance (F-score) of polarity detection by a maximum of 3.7% and 9.3% on two datasets, over the systems that use only traditional features. We perform feature significance analysis, and experiment on a held-out dataset, showing that cognitive features indeed empower sentiment ana- lyzers to handle complex constructs. 1 Introduction This paper addresses the task of Sentiment Anal- ysis (SA) - automatic detection of the sentiment polarity as positive versus negative - of user- generated short texts and sentences. Several sen- timent analyzers exist in literature today (Liu and Zhang, 2012). Recent works, such as Kouloumpis et al. (2011), Agarwal et al. (2011) and Barbosa and Feng (2010), attempt to conduct such analy- ses on user-generated content. Sentiment analysis remains a hard problem, due to the challenges it poses at the various levels, as summarized below. 1.1 Lexical Challenges Sentiment analyzers face the following three chal- lenges at the lexical level: (1) Data Sparsity, i.e., handling the presence of unseen words/phrases. (e.g., The movie is messy, uncouth, incomprehen- sible, vicious and absurd) (2) Lexical Ambiguity, e.g., finding appropriate senses of a word given the context (e.g., His face fell when he was dropped from the team vs The boy fell from the bicycle, where the verb “fell” has to be disambiguated) (3) Domain Dependency, tackling words that change polarity across domains. (e.g., the word unpre- dictable being positive in case of unpredictable movie in movie domain and negative in case of un- predictable steering in car domain). Several meth- ods have been proposed to address the different lexical level difficulties by - (a) using WordNet synsets and word cluster information to tackle lex- ical ambiguity and data sparsity (Akkaya et al., 2009; Balamurali et al., 2011; Go et al., 2009; Maas et al., 2011; Popat et al., 2013; Saif et al., 2012) and (b) mining domain dependent words (Sharma and Bhattacharyya, 2013; Wiebe and Mi- halcea, 2006). 1.2 Syntactic Challenges Difficulty at the syntax level arises when the given text follows a complex phrasal structure and, phrase attachments are expected to be resolved be- fore performing SA. For instance, the sentence A somewhat crudely constructed but gripping, quest- ing look at a person so racked with self-loathing, he becomes an enemy to his own race. requires processing at the syntactic level, before analyzing the …

Content truncated to 500 words