EmoWordNet: Automatic Expansion of Emotion Lexicon Using English WordNet

Proceedings of the 7th Joint Conference on Lexical and Computational Semantics (*SEM), pages 86–93 New Orleans, June 5-6, 2018. c⃝2018 Association for Computational Linguistics EmoWordNet: Automatic Expansion of Emotion Lexicon Using English WordNet Gilbert Badaro, Hussein Jundi†, Hazem Hajj, Wassim El-Hajj† Department of Electrical & Computer Engineering †Department of Computer Science American University of Beirut Beirut, Lebanon {ggb05;haj14;hh63;we07}@aub.edu.lb Abstract Nowadays, social media have become a plat- form where people can easily express their opinions and emotions about any topic such as politics, movies, music, electronic prod- ucts and many others. On the other hand, politicians, companies, and businesses are in- terested in analyzing automatically people’s opinions and emotions. In the last decade, a lot of efforts has been put into extracting sen- timent polarity from texts. Recently, the focus has expanded to also cover emotion recogni- tion from texts. In this work, we expand an existing emotion lexicon, DepecheMood, by leveraging semantic knowledge from English WordNet (EWN). We create an expanded lex- icon, EmoWordNet, consisting of 67K terms aligned with EWN, almost 1.8 times the size of DepecheMood. We also evaluate EmoWord- Net in an emotion recognition task using Se- mEval 2007 news headlines dataset and we achieve an improvement compared to the use of DepecheMood. EmoWordNet is publicly available to speed up research in the field on http://oma-project.com. 1 Introduction Emotion recognition models have been exten- sively explored based on different modalities such as human computer interaction (Cowie et al., 2001; Pantic and Rothkrantz, 2003; Fragopanagos and Taylor, 2005; Jaimes and Sebe, 2007; Hibbeln et al., 2017; Patwardhan and Knapp, 2017; Con- stantine et al., 2016) and facial images and ex- pressions (Goldman and Sripada, 2005; Gunes and Piccardi, 2007; Trad et al., 2012; Wegrzyn et al., 2017). Recently, special attention has been given to emotion recognition from text (Wu et al., 2006; Alm et al., 2005; Shaheen et al., 2014; Abdul- Mageed and Ungar, 2017; Badaro et al., 2018b,a). In fact, a tremendous amount of opinionated and emotionally charged text data is nowadays avail- able on the Internet due to the increase of num- ber of users of social networks such as Twitter and Facebook. For instance, Facebook reached more than 2 billion users on September 2017.1 Rec- ognizing emotions from text has several applica- tions: first, it helps companies and businesses in shaping their marketing strategies based on con- sumers’ emotions (Bougie et al., 2003); second, it allows improving typical collaborative filtering based recommender systems (Badaro et al., 2013, 2014c,d) in terms of products or advertisements recommendations (Mohammad and Yang, 2011); third, politicians can learn how to adapt their polit- ical speech based on people emotions (Pang et al., 2008) and last but not least emotion classification helps in stock market predictions (Bollen et al., 2011). While plenty of works exist for sentiment anal- ysis for different languages including analysis of social media data for sentiment characteris- tics (Al Sallab et al., 2015; Baly et al., 2014, 2017b,a), few works focused on emotion recogni- tion from text. …

Content truncated to 500 words