Sentiment classification of online reviews: using sentence-based language model

With the development of social media, the increasing online reviews of products are greatly influencing the electronic market, making sentiment classification the topic of interest for both industry and academia. This paper develops a sentence-based language model to perform sentiment classification at a fine-grained sentence level. The proposed approach applies a machine learning method to determine the sentiment polarity of a sentence at first, then designs statistical algorithm to compute the weight of the sentence in sentiment classification of the whole document and at last aggregates the weighted sentence to predict the sentiment polarity of document. Besides, experiments are carried out on corpuses in different evaluation domains and languages, and the results demonstrate the effectiveness of the sentence-based approach in obtaining a more accurate result of sentiment classification across different reviews. Furthermore, the experimental results also indicate that the position and the sentiment of a sentence have great impact on predicting the sentiment polarity of document, and corpuses with different evaluative objects, languages and sentiments also greatly influence the performance of sentiment classification. It is believed that these conclusions will be a good inspiration for similar researches.

[1]  Qiang Ye,et al.  Sentiment classification of online reviews to travel destinations by supervised machine learning approaches , 2009, Expert Syst. Appl..

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

[3]  Raymond Y. K. Lau,et al.  Automatic Domain Ontology Extraction for Context-Sensitive Opinion Mining , 2009, ICIS.

[4]  Sabine Bergler,et al.  Mining WordNet for a Fuzzy Sentiment: Sentiment Tag Extraction from WordNet Glosses , 2006, EACL.

[5]  Yücel Saygin,et al.  New Features for Sentiment Analysis: Do Sentences Matter? , 2012, SDAD@ECML/PKDD.

[6]  Liu Bo,et al.  FPGA Design of Wavelet Transform in Spatial Aircraft Image Compression , 2010 .

[7]  Wang Xiaolong.  Sentiment Classification for Chinese News Using Machine Learning Methods , 2007 .

[8]  Bin Lin,et al.  Sentiment classification for Chinese reviews: a comparison between SVM and semantic approaches , 2005, 2005 International Conference on Machine Learning and Cybernetics.

[9]  Khurshid Ahmad,et al.  Sentiment Polarity Identification in Financial News: A Cohesion-based Approach , 2007, ACL.

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

[11]  Cheng Xueqi.  Research on Sentiment Classification of Chinese Reviews Based on Supervised Machine Learning Techniques , 2007 .

[12]  Qiang Yang,et al.  Exploring in the weblog space by detecting informative and affective articles , 2007, WWW '07.

[13]  Wanxiang Che,et al.  Appraisal Expression Recognition with Syntactic Path for Sentence Sentiment Classification , 2011, Int. J. Comput. Process. Orient. Lang..

[14]  Daniel Dajun Zeng,et al.  Sentiment analysis of Chinese documents: From sentence to document level , 2009, J. Assoc. Inf. Sci. Technol..

[15]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[16]  Angela Fahrni,et al.  Old Wine or Warm Beer : Target-Specific Sentiment Analysis of Adjectives , .

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

[18]  Dipankar Das,et al.  Document Level Emotion Tagging: Machine Learning and Resource Based Approach , 2011, Computación y Sistemas.

[19]  Hsinchun Chen,et al.  Selecting Attributes for Sentiment Classification Using Feature Relation Networks , 2011, IEEE Transactions on Knowledge and Data Engineering.

[20]  Cai Qing-sheng.  Research on Feature-Selection in Chinese Text Classification , 2007 .

[21]  Li Bi-cheng.  Research of sentiment classification for netnews comments by machine learning , 2010 .

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

[23]  Hsinchun Chen,et al.  A Lexicon-Enhanced Method for Sentiment Classification: An Experiment on Online Product Reviews , 2010, IEEE Intelligent Systems.

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

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

[26]  Dipankar Das,et al.  Sentence Level Emotion Tagging on Blog and News Corpora , 2010, J. Intell. Syst..

[27]  Wang Qian.  Text Sentiment Classification Research Based on Semantic Comprehension , 2010 .

[28]  Mike Wells,et al.  Structured Models for Fine-to-Coarse Sentiment Analysis , 2007, ACL.

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

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

[31]  Huosong Xia,et al.  SVM-Based Comments Classification and Mining of Virtual Community: For Case of Sentiment Classification of Hotel Reviews , 2009 .

[32]  Janyce Wiebe,et al.  RECOGNIZING STRONG AND WEAK OPINION CLAUSES , 2006, Comput. Intell..

[33]  Wen Shi,et al.  Sentiment Classification for Movie Reviews in Chinese by Improved Semantic Oriented Approach , 2006, Proceedings of the 39th Annual Hawaii International Conference on System Sciences (HICSS'06).

[34]  Kerstin Denecke,et al.  Using SentiWordNet for multilingual sentiment analysis , 2008, 2008 IEEE 24th International Conference on Data Engineering Workshop.

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

[36]  Zili Zhang,et al.  Sentiment classification of Internet restaurant reviews written in Cantonese , 2011, Expert Syst. Appl..

[37]  Yubo Chen,et al.  Online Consumer Review: Word-of-Mouth as a New Element of Marketing Communication Mix , 2004, Manag. Sci..

[38]  Chen Lin,et al.  Research of sentiment classification for netnews comments by machine learning: Research of sentiment classification for netnews comments by machine learning , 2010 .

[39]  Claire Cardie,et al.  The Power of Negative Thinking: Exploiting Label Disagreement in the Min-cut Classification Framework , 2008, COLING.

[40]  Qin Jin.  Feature Extraction in Text Categorization , 2003 .

[41]  Yi Mao,et al.  Isotonic Conditional Random Fields and Local Sentiment Flow , 2006, NIPS.

[42]  T. V. Prabhakar,et al.  Sentence Level Sentiment Analysis in the Presence of Conjuncts Using Linguistic Analysis , 2007, ECIR.

[43]  Zhihua Wei,et al.  Feature Selection on Chinese Text Classification Using Character N-Grams , 2008, RSKT.

[44]  Pei Yin,et al.  Sentiment Feature Identification from Chinese Online Reviews , 2011 .

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