@AM: Textual Attitude Analysis Model

Proceedings of the NAACL HLT 2010 Workshop on Computational Approaches to Analysis and Generation of Emotion in Text, pages 80–88, Los Angeles, California, June 2010. c⃝2010 Association for Computational Linguistics @AM: Textual Attitude Analysis Model Alena Neviarouskaya Helmut Prendinger Mitsuru Ishizuka University of Tokyo Nat. Institute of Informatics University of Tokyo 7-3-1 Hongo, Bunkyo-ku 2-1-2 Hitotsubashi Chiyoda 7-3-1 Hongo, Bunkyo-ku Tokyo 113-8656, Japan Tokyo 101-8430, Japan Tokyo 113-8656, Japan lena@mi.ci.i.u-tokyo.ac.jp helmut@nii.ac.jp ishizuka@i.u-tokyo.ac.jp Abstract The automatic analysis and classification of text using fine-grained attitude labels is the main task we address in our research. The de- veloped @AM system relies on compositio- nality principle and a novel approach based on the rules elaborated for semantically distinct verb classes. The evaluation of our method on 1000 sentences, that describe personal expe- riences, showed promising results: average accuracy on fine-grained level was 62%, on middle level – 71%, and on top level – 88%. 1 Introduction and Related Work With rapidly growing online sources aimed at en- couraging and stimulating people’s discussions concerning personal, public or social issues (news, blogs, discussion forums, etc.), there is a great need in development of a computational tool for the analysis of people’s attitudes. According to the Appraisal Theory (Martin and White, 2005), atti- tude types define the specifics of appraisal being expressed: affect (personal emotional state), judg- ment (social or ethical appraisal of other’s behav- iour), and appreciation (evaluation of phenomena). To analyse contextual sentiment (polarity) of a phrase or a sentence, rule-based approaches (Na- sukawa and Yi, 2003; Mulder et al., 2004; Moila- nen and Pulman, 2007; Subrahmanian and Reforgiato, 2008), a machine-learning method us- ing not only lexical but also syntactic features (Wilson et al., 2005), and a model of integration of machine learning approach with compositional semantics (Choi and Cardie, 2008) were proposed. With the aim to recognize fine-grained emotions from text on the level of distinct sentences, re- searchers have employed a keyword spotting tech- nique (Olveres et al., 1998; Chuang and Wu, 2004; Strapparava et al., 2007), a technique calculating emotion scores using Pointwise Mutual Informa- tion (PMI) (Kozareva et al., 2007), an approach inspired by common-sense knowledge (Liu et al., 2003), rule-based linguistic approaches (Boucou- valas, 2003; Chaumartin, 2007), machine-learning methods (Alm, 2008; Aman and Szpakowicz, 2008; Strapparava and Mihalcea, 2008), and an ensemble based multi-label classification technique (Bhowmick et al., 2009). Early attempts to focus on distinct attitude types in the task of attitude analysis were made by Ta- boada and Grieve (2004), who determined a poten- tial value of adjectives for affect, judgement and appreciation by calculating the PMI with the pro- noun-copular pairs ‘I was (affect)’, ‘He was (judgement)’, and ‘It was (appreciation)’, and Whitelaw et al. (2005), who used machine learning technique (SVM) with fine-grained semantic dis- tinctions in features (attitude type, orientation) in combination with “bag of words” to classify movie reviews. However, the concentration only on ad- jectives, that express appraisal, and their modifiers, greatly narrows the potential of the Whitelaw et al.’s (2005) …

Content truncated to 500 words