论文信息 - Exploiting Hierarchical Discourse Structure for Review Sentiment Analysis

Exploiting Hierarchical Discourse Structure for Review Sentiment Analysis

The overall sentiment of a text is critically affected by its discourse structure. For the first time, this paper incorporates hierarchical discourse structure into an unsupervised sentiment analysis framework. Experimental results show that by integrating discourse structure, the performance of sentiment analysis is improved by 1.9% (from 85.1% to 87.0%), demonstrating the effectiveness of exploiting discourse structure for sentiment analysis.

Fei Wang | Yunfang Wu | Fei Wang | Yunfang Wu

[1] Jian Su,et al. Kernel Based Discourse Relation Recognition with Temporal Ordering Information , 2010, ACL.

[2] Swapna Somasundaran,et al. Discourse Level Opinion Interpretation , 2008, COLING.

[3] Likun Qiu,et al. SELC: a self-supervised model for sentiment classification , 2009, CIKM.

[4] Uzay Kaymak,et al. Polarity analysis of texts using discourse structure , 2011, CIKM '11.

[5] Annie Zaenen,et al. Contextual Valence Shifters , 2006, Computing Attitude and Affect in Text.

[6] Pushpak Bhattacharyya,et al. Sentiment Analysis in Twitter with Lightweight Discourse Analysis , 2012, COLING.

[7] Shafiq R. Joty,et al. A Novel Discriminative Framework for Sentence-Level Discourse Analysis , 2012, EMNLP.

[8] Graeme Hirst,et al. Text-level Discourse Parsing with Rich Linguistic Features , 2012, ACL.

[9] Mitsuru Ishizuka,et al. HILDA: A Discourse Parser Using Support Vector Machine Classification , 2010, Dialogue Discourse.

[10] Wei Gao,et al. Unsupervised Discovery of Discourse Relations for Eliminating Intra-sentence Polarity Ambiguities , 2011, EMNLP.

[11] Fei Wang,et al. Exploiting Discourse Relations for Sentiment Analysis , 2012, COLING.

[12] Lise Getoor,et al. Supervised and Unsupervised Methods in Employing Discourse Relations for Improving Opinion Polarity Classification , 2009, EMNLP.