Sentence Subjectivity Analysis in Social Domains

Subjectivity analysis recognizes the contextual polarity of opinions, attitudes, emotions, feelings etc. regarding products, services, topics, or issues. Subjectivity classification categorizes the given text as subjective or objective. While an objective text contains one or more facts about a product or an issue, a subjective text expresses author's opinions. Statistical analysis shows that subjectivity analysis of social issues is different from that of products. This paper focuses on subjectivity analysis of social issues. Subjectivity of a document strongly depends on its sentences. Hence, a lexical-syntactical approach is proposed to recognize and classify subjectivity at the sentence level. This approach considers the role of various opinion terms especially verbs on opinions regarding social issues. Evaluation of the proposed approach on a data-set consisting comments about abortion shows that it slightly outperforms other similar works. It has a good accuracy especially on the strong sentences which express explicit opinions. Its reasonable F-measure demonstrates a good balance between the precision and recall which makes it suitable for applications such as sentiment polarity classification, text sentiment summarization, and opinion question answering.

[1]  Rohini K. Srihari,et al.  Using Verbs and Adjectives to Automatically Classify Blog Sentiment , 2006, AAAI Spring Symposium: Computational Approaches to Analyzing Weblogs.

[2]  Bing Liu,et al.  Opinion observer: analyzing and comparing opinions on the Web , 2005, WWW '05.

[3]  Janyce Wiebe,et al.  Development and Use of a Gold-Standard Data Set for Subjectivity Classifications , 1999, ACL.

[4]  Ellen Riloff,et al.  Finding Mutual Benefit between Subjectivity Analysis and Information Extraction , 2011, IEEE Transactions on Affective Computing.

[5]  Vidyasagar Potdar,et al.  A state of the art opinion mining and its application domains , 2009, 2009 IEEE International Conference on Industrial Technology.

[6]  Claire Cardie,et al.  Annotating Expressions of Opinions and Emotions in Language , 2005, Lang. Resour. Evaluation.

[7]  Ali A. Ghorbani,et al.  Sentiment Analysis of Social Issues , 2012, 2012 International Conference on Social Informatics.

[8]  Ellen Riloff,et al.  Exploiting Subjectivity Classification to Improve Information Extraction , 2005, AAAI.

[9]  Weblog Wikipedia,et al.  In Wikipedia the Free Encyclopedia , 2005 .

[10]  Ali A. Ghorbani,et al.  Verb Oriented Sentiment Classification , 2012, 2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology.

[11]  Jeonghee Yi,et al.  Sentiment analysis: capturing favorability using natural language processing , 2003, K-CAP '03.

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

[13]  Andrea Esuli,et al.  SENTIWORDNET: A Publicly Available Lexical Resource for Opinion Mining , 2006, LREC.

[14]  Bing Liu,et al.  Sentiment Analysis and Subjectivity , 2010, Handbook of Natural Language Processing.

[15]  Shishir K. Shandilya,et al.  Automatic Opinion Extraction from Web Documents , 2009, 2009 International Conference on Computer and Automation Engineering.

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

[17]  Lei Zhang,et al.  Entity discovery and assignment for opinion mining applications , 2009, KDD.

[18]  David M. Pennock,et al.  Mining the peanut gallery: opinion extraction and semantic classification of product reviews , 2003, WWW '03.

[19]  Janyce Wiebe,et al.  Recognizing Arguing Subjectivity and Argument Tags , 2012, ExProM@ACL.

[20]  Rada Mihalcea,et al.  Word Sense and Subjectivity , 2006, ACL.

[21]  Swapna Somasundaran,et al.  Recognizing Stances in Ideological On-Line Debates , 2010, HLT-NAACL 2010.

[22]  Bo Pang,et al.  Thumbs up? Sentiment Classification using Machine Learning Techniques , 2002, EMNLP.

[23]  Eric K. Ringger,et al.  Pulse: Mining Customer Opinions from Free Text , 2005, IDA.

[24]  Dan Klein,et al.  Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network , 2003, NAACL.