The viability of web-derived polarity lexicons

We examine the viability of building large polarity lexicons semi-automatically from the web. We begin by describing a graph propagation framework inspired by previous work on constructing polarity lexicons from lexical graphs (Kim and Hovy, 2004; Hu and Liu, 2004; Esuli and Sabastiani, 2009; BlairGoldensohn et al., 2008; Rao and Ravichandran, 2009). We then apply this technique to build an English lexicon that is significantly larger than those previously studied. Crucially, this web-derived lexicon does not require WordNet, part-of-speech taggers, or other language-dependent resources typical of sentiment analysis systems. As a result, the lexicon is not limited to specific word classes

• Type: Journal
• Year: 2010
• Where: NAACL
• Authors: Leonid Velikovich, Sasha Blair-Goldensohn, Kerry Hannan, Ryan T. McDonald
• Keywords: Computational Linguistics, Large Polarity Lexicons, Lexicon, NAACL 2010, Polarity Lexicons