Aggregation using ConceptNet Ontology

Sentiment analysis of reviews traditionally ignored the association between the features of the given product domain. The hierarchical relationship between the features of a product and their associated sentiment that influence the polarity of a review is not dealt with very well. In this work, we analyze the influence of the hierarchical relationship between the product attributes and their sentiments on the overall review polarity. ConceptNet is used to automatically create a product specific ontology that depicts the hierarchical relationship between the product attributes. The ontology tree is annotated with feature-specific polarities which are aggregated bottom-up, exploiting the ontological information, to find the overall review polarity. We propose a weakly supervised system that achieves a reasonable performance improvement over the baseline without requiring any tagged training data.

[1]  Michael L. Littman,et al.  Measuring praise and criticism: Inference of semantic orientation from association , 2003, TOIS.

[2]  Bing Liu,et al.  Mining and summarizing customer reviews , 2004, KDD.

[3]  Alistair Kennedy,et al.  Sentiment Classification of Movie and Product Reviews Using Contextual Valence Shifters , 2005 .

[4]  Pushpak Bhattacharyya,et al.  WikiSent : Weakly Supervised Sentiment Analysis Through Extractive Summarization With Wikipedia , 2012, ECML/PKDD.

[5]  Dominique Estival,et al.  Towards Ontology-based Natural Language Processing , 2004, NLPXML@ACL.

[6]  Nigel Collier,et al.  Sentiment Analysis using Support Vector Machines with Diverse Information Sources , 2004, EMNLP.

[7]  S. Guadarrama.  Concept-Analyzer : A tool for analyzing fuzzy concepts , 2008 .

[8]  Andrea Esuli,et al.  SentiWordNet 3.0: An Enhanced Lexical Resource for Sentiment Analysis and Opinion Mining , 2010, LREC.

[9]  Peter D. Turney.  Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews , 2002, ACL.

[10]  Janyce Wiebe,et al.  Effects of Adjective Orientation and Gradability on Sentence Subjectivity , 2000, COLING.

[11]  ChengXiang Zhai,et al.  Tapping into knowledge base for concept feedback: leveraging conceptnet to improve search results for difficult queries , 2012, WSDM '12.

[12]  Denzil Correa,et al.  Generating Domain-Specific Ontology from Common-Sense Semantic Network for Target-Specific Sentiment Analysis , 2010 .

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

[14]  Kathleen R. McKeown,et al.  Predicting the semantic orientation of adjectives , 1997 .

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

[16]  John Blitzer,et al.  Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification , 2007, ACL.

[17]  Yue Lu,et al.  Latent aspect rating analysis without aspect keyword supervision , 2011, KDD.

[18]  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.

[19]  Tianfang Yao,et al.  Combining dependency parsing with shallow semantic analysis for Chinese opinion-element relation identification , 2010, 2010 4th International Universal Communication Symposium.

[20]  Xuanjing Huang,et al.  Phrase Dependency Parsing for Opinion Mining , 2009, EMNLP.

[21]  J. Kamps,et al.  Words with attitude , 2002 .

[22]  Pushpak Bhattacharyya,et al.  Feature Specific Sentiment Analysis for Product Reviews , 2012, CICLing.

[23]  Hugo Liu,et al.  ConceptNet — A Practical Commonsense Reasoning Tool-Kit , 2004 .