Happy Accident: A Sentiment Composition Lexicon for Opposing Polarity Phrases

Happy Accident: A Sentiment Composition Lexicon for Opposing Polarity Phrases Svetlana Kiritchenko and Saif M. Mohammad National Research Council Canada 1200 Montreal Rd., Ottawa, ON, Canada svetlana.kiritchenko@nrc-cnrc.gc.ca, saif.mohammad@nrc-cnrc.gc.ca Abstract Sentiment composition is the determining of sentiment of a multi-word linguistic unit, such as a phrase or a sentence, based on its constituents. We focus on sentiment composition in phrases formed by at least one positive and at least one negative word—phrases like happy accident and best winter break. We refer to such phrases as opposing polarity phrases. We manually annotate a collection of opposing polarity phrases and their constituent single words with real-valued sentiment intensity scores using a method known as Best– Worst Scaling. We show that the obtained annotations are consistent. We explore the entries in the lexicon for linguistic regularities that govern sentiment composition in opposing polarity phrases. Finally, we list the current and possible future applications of the lexicon. Keywords: sentiment composition, sentiment lexicon, opposing polarity phrases, Best–Worst Scaling, crowdsourcing 1. Introduction Words have associations with sentiment. For example, hon- est and competent are associated with positive sentiment, whereas dishonest and dull are associated with negative sentiment. Further, the degree of positivity (or negativity), also referred to as sentiment intensity, can vary. For exam- ple, most people will agree that succeed is more positive (or less negative) than improve, and failure is more negative (or less positive) than decline. Sentiment associations are commonly captured in senti- ment lexicons—lists of associated word–sentiment pairs (optionally with a score indicating the degree of associa- tion). They are mostly used in sentiment analysis, but are also valuable in stance detection (Mohammad et al., 2016a; Mohammad et al., 2016b), literary analysis (Hartner, 2013; Kleres, 2011), and other applications. Manually created sentiment lexicons usually include only single words. However, the sentiment of a phrase can differ significantly from the sentiment of its constituent words. Sentiment composition is the determining of sentiment of a multi-word linguistic unit, such as a phrase or a sen- tence, based on its constituents. Lexicons that include sen- timent associations for phrases as well as their constituent words can be very useful in studying sentiment composi- tion. We will refer to them as sentiment composition lexi- cons (SCLs). In this work, we focus on sentiment composition in phrases that include at least one positive and at least one negative word—for example, phrases such as happy accident, best winter break, couldn’t stop smiling, and lazy sundays.1 We refer to them as opposing polarity phrases. We describe how we created a sentiment composition lexicon for op- posing polarity phrases and their constituent words. Most existing manually created sentiment lexicons provide only lists of positive and negative words with very coarse levels of sentiment (Stone et al., 1966; Wilson et al., 2005; Mohammad and Turney, 2013). The coarse-grained distinc- tions may be less useful in downstream applications than 1Observe that lazy is associated with negative sentiment whereas sundays is associated with positive sentiment. having access to fine-grained (real-valued) sentiment asso- ciation scores …

Content truncated to 500 words