Finding Opinion Strength Using Rule-Based Parsing for Arabic Sentiment Analysis

With increasing interest in sentiment analysis research and opinionated web content always on the rise, focus on analysis of text in various domains and different languages is a relevant and important task. This paper explores the problems of sentiment analysis and opinion strength measurement using a rule-based approach tailored to the Arabic language. The approach takes into account language-specific traits that are valuable to syntactically segment a text, and allow for closer analysis of opinion-bearing language queues. By using an adapted sentiment lexicon along with sets of opinion indicators, a rule-based methodology for opinion-phrase extraction is introduced, followed by a method to rate the parsed opinions and offer a measure of opinion strength for the text under analysis. The proposed method, even with a small set of rules, shows potential for a simple and scalable opinion-rating system, which is of particular interest for morphologically-rich languages such as Arabic.

[1]  Ellen Riloff,et al.  Learning Extraction Patterns for Subjective Expressions , 2003, EMNLP.

[2]  Muhammad Abdul-Mageed,et al.  Subjectivity and Sentiment Analysis of Modern Standard Arabic , 2011, ACL.

[3]  Hong Yu,et al.  Towards Answering Opinion Questions: Separating Facts from Opinions and Identifying the Polarity of Opinion Sentences , 2003, EMNLP.

[4]  Ana María Martínez Enríquez,et al.  Lexicon Based Sentiment Analysis of Urdu Text Using SentiUnits , 2010, MICAI.

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

[6]  Hsinchun Chen,et al.  Sentiment analysis in multiple languages: Feature selection for opinion classification in Web forums , 2008, TOIS.

[7]  Bing Liu,et al.  Sentiment Analysis and Opinion Mining , 2012, Synthesis Lectures on Human Language Technologies.

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

[9]  Xin Wang,et al.  Chinese Sentence-Level Sentiment Classification Based on Fuzzy Sets , 2010, COLING.

[10]  Janyce Wiebe,et al.  Recognizing subjectivity: a case study in manual tagging , 1999, Natural Language Engineering.

[11]  Deba Prasad Mandal,et al.  Finding Opinion Strength Using Fuzzy Logic on Web Reviews , 2011 .

[12]  Janyce Wiebe,et al.  Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis , 2005, HLT.

[13]  Karin C. Ryding,et al.  A Reference Grammar of Modern Standard Arabic , 2005 .

[14]  S.N. Saleh,et al.  A feature selection algorithm with redundancy reduction for text classification , 2007, 2007 22nd international symposium on computer and information sciences.

[15]  Yasser El-Sonbaty,et al.  ALQASIM: Arabic Language Question Answer Selection in Machines , 2013, CLEF.

[16]  Nizar Habash,et al.  Introduction to Arabic Natural Language Processing , 2010, Introduction to Arabic Natural Language Processing.

[17]  Luis Alfonso Ureña López,et al.  OCA: Opinion corpus for Arabic , 2011, J. Assoc. Inf. Sci. Technol..

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

[19]  Claire Cardie,et al.  OpinionFinder: A System for Subjectivity Analysis , 2005, HLT.