Better Document-level Sentiment Analysis from RST Discourse Parsing

Discourse structure is the hidden link between surface features and document-level properties, such as sentiment polarity. We show that the discourse analyses produced by Rhetorical Structure Theory (RST) parsers can improve document-level sentiment analysis, via composition of local information up the discourse tree. First, we show that reweighting discourse units according to their position in a dependency representation of the rhetorical structure can yield substantial improvements on lexicon-based sentiment analysis. Next, we present a recursive neural network over the RST structure, which offers significant improvements over classificationbased methods.

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

[2]  Jacob Eisenstein,et al.  Discourse Connectors for Latent Subjectivity in Sentiment Analysis , 2013, NAACL.

[3]  Daniel Marcu,et al.  The automatic construction of large-scale corpora for summarization research , 1999, SIGIR '99.

[4]  Navneet Kaur,et al.  Opinion mining and sentiment analysis , 2016, 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom).

[5]  Bo Pang,et al.  A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts , 2004, ACL.

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

[7]  Maite Taboada,et al.  Lexicon-Based Methods for Sentiment Analysis , 2011, CL.

[8]  Alice H. Oh,et al.  Do You Feel What I Feel? Social Aspects of Emotions in Twitter Conversations , 2012, ICWSM.

[9]  Noah A. Smith,et al.  Narrative framing of consumer sentiment in online restaurant reviews , 2014, First Monday.

[10]  Eduard H. Hovy,et al.  Recursive Deep Models for Discourse Parsing , 2014, EMNLP.

[11]  Maite Taboada,et al.  Not All Words Are Created Equal: Extracting Semantic Orientation as a Function of Adjective Relevance , 2007, Australian Conference on Artificial Intelligence.

[12]  David E. Losada,et al.  Rhetorical Structure Theory for polarity estimation: An experimental study , 2014, Data Knowl. Eng..

[13]  Marshall S. Smith,et al.  The general inquirer: A computer approach to content analysis. , 1967 .

[14]  William C. Mann,et al.  Discourse Structures for Text Generation , 1984, ACL.

[15]  Giuseppe Carenini,et al.  Abstractive Summarization of Product Reviews Using Discourse Structure , 2014, EMNLP.

[16]  Daniel Marcu,et al.  Sentence Level Discourse Parsing using Syntactic and Lexical Information , 2003, NAACL.

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

[18]  Noah A. Smith,et al.  Dependency Parsing , 2009, Encyclopedia of Artificial Intelligence.

[19]  Heiner Stuckenschmidt,et al.  Fine-Grained Sentiment Analysis with Structural Features , 2011, IJCNLP.

[20]  Lei Zhang,et al.  Sentiment Analysis and Opinion Mining , 2017, Encyclopedia of Machine Learning and Data Mining.

[21]  Kenji Sagae,et al.  Analysis of Discourse Structure with Syntactic Dependencies and Data-Driven Shift-Reduce Parsing , 2009, IWPT.

[22]  Claire Cardie,et al.  Context-aware Learning for Sentence-level Sentiment Analysis with Posterior Regularization , 2014, ACL.

[23]  Ronen Feldman,et al.  Techniques and applications for sentiment analysis , 2013, CACM.

[24]  Benno Stein,et al.  Modeling Review Argumentation for Robust Sentiment Analysis , 2014, COLING.

[25]  Masaaki Nagata,et al.  Dependency-based Discourse Parser for Single-Document Summarization , 2014, EMNLP.

[26]  Jure Leskovec,et al.  A computational approach to politeness with application to social factors , 2013, ACL.

[27]  Geoffrey E. Hinton.  Tensor Product Variable Binding and the Representation of Symbolic Structures in Connectionist Systems , 1991 .

[28]  J. Pennebaker,et al.  The Psychological Meaning of Words: LIWC and Computerized Text Analysis Methods , 2010 .

[29]  Philipp Koehn,et al.  Synthesis Lectures on Human Language Technologies , 2016 .

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

[31]  Masaaki Nagata,et al.  Single-Document Summarization as a Tree Knapsack Problem , 2013, EMNLP.

[32]  Andrew Y. Ng,et al.  Parsing Natural Scenes and Natural Language with Recursive Neural Networks , 2011, ICML.

[33]  Daniel Marcu.  The rhetorical parsing of natural language texts , 1997 .

[34]  TaboadaMaite,et al.  Lexicon-based methods for sentiment analysis , 2011 .

[35]  Jacob Eisenstein,et al.  Representation Learning for Text-level Discourse Parsing , 2014, ACL.

[36]  Vasileios Hatzivassiloglou,et al.  Predicting the Semantic Orientation of Adjectives , 1997, ACL.

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

[38]  Maria das Graças Volpe Nunes,et al.  A comprehensive comparative evaluation of RST-based summarization methods , 2010, TSLP.

[39]  Tejashri Inadarchand Jain,et al.  Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis , 2010 .

[40]  Shafiq R. Joty,et al.  CODRA: A Novel Discriminative Framework for Rhetorical Analysis , 2015, CL.

[41]  Fei Wang,et al.  Exploiting Hierarchical Discourse Structure for Review Sentiment Analysis , 2013, 2013 International Conference on Asian Language Processing.

[42]  Ivan Titov,et al.  A Bayesian Model for Joint Unsupervised Induction of Sentiment, Aspect and Discourse Representations , 2013, ACL.

[43]  Christopher Potts,et al.  Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank , 2013, EMNLP.

[44]  Christoph Goller,et al.  Learning task-dependent distributed representations by backpropagation through structure , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

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