A Hybrid Framework Based on PSO and Neutrosophic Set for Document Level Sentiment Analysis

Opinion mining for document level has undergone different testing process in the last few years. A lot of research work has contributed for analysis of such reviews to extract the sentiment associated with the texts. Fuzzy technologies and machine learning are the most explored area for sentiment analysis. In this paper, Particle Swarm Optimization (PSO), an Evolutionary algorithm has been hybridized with Neutrosophic Set concept to generate a ternary classifier. PSO has a simple and robust method for finding out global optima on huge sample points. The sentiment of a large text is classified as a ternary value: Positive, Negative or Neutral. This method is suitable to classify large sized text. This hybridization has not been dealt in the literature. Large sized positive, negative and neutral text have been generated from existing review comments of products and plots of movies. This method will be highly useful for classifying documents like review comments on research papers from different researchers, political analysis on a subject or police verification on any news for sentiment polarity finding and many more.

[1]  Claire Cardie,et al.  Multi-Level Structured Models for Document-Level Sentiment Classification , 2010, EMNLP.

[2]  C. Ashbacher.  Introduction to neutrosophic logic , 2002 .

[3]  Florentin Smarandache,et al.  Neutrosophic Modal Logic , 2017 .

[4]  Yang Liu,et al.  Multi-class sentiment classification: The experimental comparisons of feature selection and machine learning algorithms , 2017, Expert Syst. Appl..

[5]  Dipankar Das,et al.  Enhanced SenticNet with Affective Labels for Concept-Based Opinion Mining , 2013, IEEE Intelligent Systems.

[6]  Namita Mittal,et al.  Concept-Level Sentiment Analysis with Dependency-Based Semantic Parsing: A Novel Approach , 2015, Cognitive Computation.

[7]  Indrajit Chakrabarti,et al.  Improving the Performance of Deep Learning Based Speech Enhancement System Using Fuzzy Restricted Boltzmann Machine , 2017, PReMI.

[8]  Usha Devi Gandhi,et al.  Classifying streaming of Twitter data based on sentiment analysis using hybridization , 2018, Neural Computing and Applications.

[9]  Swati Aggarwal,et al.  Neutrosophic classifier: An extension of fuzzy classifer , 2014, Appl. Soft Comput..

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

[11]  William W. L. Cheung,et al.  A Fuzzy Logic Expert System to Estimate Intrinsic Extinction Vulnerabilities of Marine Fishes to Fishing , 2004 .

[12]  Santanu Kumar Rath,et al.  Document-level sentiment classification using hybrid machine learning approach , 2017, Knowledge and Information Systems.

[13]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[14]  Mauro Dragoni,et al.  Propagating and Aggregating Fuzzy Polarities for Concept-Level Sentiment Analysis , 2015, Cognitive Computation.

[15]  Richa Sharma,et al.  Opinion mining of movie reviews at document level , 2014, ArXiv.

[16]  Kyung Sup Kwak,et al.  Fuzzy Ontology-Based Sentiment Analysis of Transportation and City Feature Reviews for Safe Traveling , 2017, ArXiv.

[17]  Chunfeng Yuan,et al.  Exploring overall opinions for document level sentiment classification with structural SVM , 2017, Multimedia Systems.

[18]  Xiaodong Li,et al.  Cooperatively Coevolving Particle Swarms for Large Scale Optimization , 2012, IEEE Transactions on Evolutionary Computation.

[19]  Tomoaki Ohtsuki,et al.  A Pattern-Based Approach for Multi-Class Sentiment Analysis in Twitter , 2017, IEEE Access.

[20]  Yue Zhang,et al.  Learning Domain Representation for Multi-Domain Sentiment Classification , 2018, NAACL.

[21]  Felix T.S. Chan,et al.  A CMPSO Algorithm Based Approach to Solve the Multi-plant Supply Chain Problem , 2007 .

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

[23]  Avdesh Mishra,et al.  Multiclass patent document classification , 2017, Artif. Intell. Res..

[24]  Bhawna Nigam,et al.  Categorizing the Document Using Multi Class Classification in Data Mining , 2011, 2011 International Conference on Computational Intelligence and Communication Networks.

[25]  Mohd Ridzwan Yaakub,et al.  Metaheuristic algorithms for feature selection in sentiment analysis , 2015, 2015 Science and Information Conference (SAI).

[26]  Akshi Kumar,et al.  A Survey on Sentiment Analysis using Swarm Intelligence , 2016 .

[27]  Shu-Kai S. Fan,et al.  A parallel particle swarm optimization algorithm for multi-objective optimization problems , 2009 .

[28]  Mahmoud Omid,et al.  Intelligent Control Based Fuzzy Logic for Automation of Greenhouse Irrigation System and Evaluation in Relation to Conventional Systems , 2009 .

[29]  Li Bing,et al.  A Fuzzy Logic Approach for Opinion Mining on Large Scale Twitter Data , 2014, 2014 IEEE/ACM 7th International Conference on Utility and Cloud Computing.

[30]  Florentin Smarandache.  Neutrosophic Theory and its Applications, Collected Papers, Vol. 1 , 2014 .

[31]  Xin Yao,et al.  Large scale evolutionary optimization using cooperative coevolution , 2008, Inf. Sci..

[32]  Burairah Hussin,et al.  Opinion Mining of Movie Review using Hybrid Method of Support Vector Machine and Particle Swarm Optimization , 2013 .

[33]  Mihaela Colhon,et al.  How Objective a Neutral Word Is? A Neutrosophic Approach for the Objectivity Degrees of Neutral Words , 2017, Symmetry.

[34]  Sheng-Tun Li,et al.  A fuzzy conceptualization model for text mining with application in opinion polarity classification , 2013, Knowl. Based Syst..