Significant growth of e-commerce has led to huge number of reviews for a product or service. It provides different aspects of service or a product for the users. Sentiment analysis techniques are used to extract feature and opinion in a concise summary form from the customer reviews. Feature based summarization system uses term frequency and feature opinion learner to generate the summary. Fitness value based binary particle swarm optimization for feature selection is proposed to select the best feature subset. The feature selection in BPSO uses fitness value based on the term frequency and opinion score. In BPSO efficient summary is generated using the multi-objective function based on feature weight score and similarity between term frequency and position. The Recall-Oriented Understanding for Gisting Evaluation (ROUGE) toolkit is used to measure the performance of the Multi objective fitness based BPSO. An experimental result proves that multi-objective FBPSO algorithm improves the feature selection and summary generation accuracy.

Feature selection, Multi-objective, Fitness, Binary Particle Swarm Optimization, Summarization

[1] ArtiBuche, Dr.M.BChandak, Akshay Zadgaonkar, “Opinion Mining and Analysis: A Survey”, Proceedings of the International Journal on Natural Language Computing, Volume 2, No. 3, pp. 39-48, 2013.
[2] Gamgarn Somprasertsri, Pattarachai Lalitrojwong, “Mining Feature-Opinion in Online Customer Reviews for Opinion Summarization”, Journal of Universal Computer Science, Vol.16, No.6, pp. 938-955, 2010.
[3] Dim En Nyaung, Thin Lai Lai Thein, “Feature-Based Summarizing and Ranking from Customer Reviews”, International Journal of Computer, Electrical, Automation, Control and Information Engineering Vol: 9, No: 3, 2015.
[4] Li-Ping Jing, Hou-Kuan Huang, Hong-Bo, “Improved Feature Selection Approach TFIDF in Text Mining”, Proceedings of the First International Conference on Machine Learning and Cybernetics, Vol. 2, 2002.
[5] J. Wiebe, E. Riloff, “Creating Subjective and Objective Sentence Classifiers from Unannotated Texts”, In Proceedings of the 6th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing-10), Vol: 3406, pp. 486-497, 2010.
[6] Florian Wogenstein, J. Drescher, D. Reinel, S. Rill, J. Scheidt, “Evaluation of an Algorithm for Aspect-Based Opinion Mining Using a Lexicon-Based Approach”, WISDOM ’13, Proceedings of the Second International Workshop on Issues of Sentiment Discovery and Opinion Mining, Article No. 5, 2013.
[7] Bing Xue, Mengjie Zhang and Will N. Browne, ‘Single Feature Ranking and Binary Particle Swarm Optimisation Based Feature Subset Ranking for Feature Selection’, Proceedings of the Thirty-Fifth Australasian Computer Science Conference, Melbourne, Australia, Vol.122, ACS, pp. 27-36, 2012.
[8] Zhou Z, Liu X, Li P, Shang L, “Feature selection method with Proportionate Fitness based Binary Particle Swarm Optimization”, In: Simulated evolution and learning, pp. 582–592. Springer, New York, 2014.
[9] Ahmed M. Al-Zahrani, Hassan Mathkour, Hassan Abdalla, “PSO-Based Feature Selection for Arabic Text Summarization”, Journal of Universal Computer Science, Vol. 21, No.11, pp. 1454-1469, 2015.
[10] Rasim M. Alguliev, Ramiz M. Aliguliyev, Nijat R. Isazade, “MR&MR-SUM: Maximum Relevance and Minimum Redundancy Document Summarization Model”, International Journal of Information Technology and Decision Making, Vol.12, No.3, pp. 361-393, 2013.
[11] Mohammed Salem Binwahlan , Naomie Salim2 , Ladda Suanmali, “Swarm Based Features Selection for Text Summarization”, International Journal of Computer Science and Network Security, Vol.9, No.1, 2009.
[12] Houda Oufaida, Omar Nouali, Philippe Blache, "Minimum Redundancy and Maximum Relevance for Single and Multi-document Arabic Text Summarization”, Journal of King Saud University – Computer and Information Sciences, Volume 26, Issue 4, pp. 450–461, 2014.
[13] B.Suganya, V.Priya, “Particle Swarm Optimization Based Feature Selection and Summarization of Customer Reviews”, International Conference on Emerging trends in Engineering, Science and Sustainable Technology, pp. 131-135, 2017.
[14] Lin Shang, Zhe Zhou, Xing Liu, “Particle Swarm Optimization-based Feature Selection in Sentiment Classification”, Journal of Soft Computing – A Fusion of Foundations, Methodologies and Applications, Vol.20, Issue.10, pp. 3821-3834, 2016.
[15] Bing Xue, Mengjie Zhang and Will N.Browne, “Particle Swarm Optimization for Feature Selection in Classification: A Multi-Objective Approach”, IEEE Transactions on Cybernetics, 43(6), pp. 1656-71, 2012.
[16] Josef Steinberger, Karel Jezek, “Evaluation Measures For Text Summarization”, Computing and Informatics, Vol. 28, pp. 1001–1026, 2009.