Building Lexicon for Sentiment Analysis from Massive Collection of HTML Documents

Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pp. 1075–1083, Prague, June 2007. c⃝2007 Association for Computational Linguistics Building Lexicon for Sentiment Analysis from Massive Collection of HTML Documents Nobuhiro Kaji and Masaru Kitsuregawa Institute of Industrial Science, University of Tokyo 4-6-1 Komaba, Meguro-ku, Tokyo 153-8505 Japan �kaji,kitsure �@tkl.iis.u-tokyo.ac.jp Abstract Recognizing polarity requires a list of po- lar words and phrases. For the purpose of building such lexicon automatically, a lot of studies have investigated (semi-) unsuper- vised method of learning polarity of words and phrases. In this paper, we explore to use structural clues that can extract polar sentences from Japanese HTML documents, and build lexicon from the extracted po- lar sentences. The key idea is to develop the structural clues so that it achieves ex- tremely high precision at the cost of recall. In order to compensate for the low recall, we used massive collection of HTML docu- ments. Thus, we could prepare enough polar sentence corpus. 1 Introduction Sentiment analysis is a recent attempt to deal with evaluative aspects of text. In sentiment analysis, one fundamental problem is to recognize whether given text expresses positive or negative evaluation. Such property of text is called polarity. Recognizing po- larity requires a list of polar words and phrases such as ’good’, ’bad’ and ’high performance’ etc. For the purpose of building such lexicon automatically, a lot of studies have investigated (semi-) unsupervised approach. So far, two kinds of approaches have been pro- posed to this problem. One is based on a the- saurus. This method utilizes synonyms or glosses of a thesaurus in order to determine polarity of words (Kamps et al., 2004; Hu and Liu, 2004; Kim and Hovy, 2004; Esuli and Sebastiani, 2005). The sec- ond approach exploits raw corpus. Polarity is de- cided by using co-occurrence in a corpus. This is based on a hypothesis that polar phrases conveying the same polarity co-occur with each other. Typ- ically, a small set of seed polar phrases are pre- pared, and new polar phrases are detected based on the strength of co-occurrence with the seeds (Hatzi- vassiloglous and McKeown, 1997; Turney, 2002; Kanayama and Nasukawa, 2006). As for the second approach, it depends on the definition of co-occurrence whether the hypothe- sis is appropriate or not. In Turney’s work, the co-occurrence is considered as the appearance in the same window (Turney, 2002). Although this idea is simple and feasible, there is a room for im- provement. According to Kanayama’s investiga- tion, the hypothesis is appropriate in only 60% of cases if co-occurrence is defined as the appearance in the same window1. In Kanayama’s method, the co-occurrence is considered as the appearance in intra- or inter-sentential context (Kanayama and Na- sukawa, 2006). They reported that the precision was boosted to 72.2%, but it is still not enough. There- fore, we think that the above hypothesis is often in- appropriate in practice, and this fact is the biggest obstacle to …

Content truncated to 500 words