Gain ratio feed forward neural network algorithm to improve classification accuracy
In the field of information technology, there is revolution that has led to an abundance of information in every field through Internet. The rapid growth in the mobile devices indicates that the users and industry are getting more at ease with the mobile environment. An incredible amount of mobile learning systems and usersâ€™ opinion about these apps are available in the form of reviews on the websites or in the social blogs or feedback. To classify these opinions, Neural Networks algorithm is mostly used to obtain high accuracy. To mine mobile learning app reviews, Gain Ratio based neural network algorithm for opinion mining system is proposed in this research paper. The main focus is to extract the polarity of the reviews, opinion it and conclude whether these reviews are positive or negative or neutral. This research work consists of four steps (i) Estimate score of the words in the review document by using Singular Value Decomposition (SVD) (ii) Feed forward the top ranked words with its weights from the input layer to hidden layer (iii) Calculate gain ratio and select top five positive and negative attributes (iv) Pass the selected attributes from input layer to output layer. This customized neural network classification algorithm helps to improve the classification accuracy.
 Dave, D., Lawrence A., and Pennock D. Mining the Peanut Gallery Opinion Extraction and Semantic Classification of Product Reviews, Proceedings of International World Wide Web Conference (WWW â€™03), 2003.
 Talemura Junichi, â€œVirtual reviews for collaborative exploration of movie reviewsâ€, in proceedings of Intelligent User Interfaces (IUI) pages 272-275, 2000.
 S. Thanangthanakij, E. Pacharawongsakda, N. Tongtep, P. Aimmanee, T. Theeramunkong, â€œAn Empirical Study on Multi- Dimensional Sentiment Analysis from User Service Reviewsâ€, Knowledge, Information and Creativity Support Systems, pp. 58 â€“ 65, IEEE, 2012.
 C. Zhang, W. Zuo, T. Peng and F. He, â€œSentiment Classification Reviews Using Machine Learning Methods Based on String ernelâ€, Convergence and Hybrid Information Technology, Vol. 2, pp. 909 â€“ 914, IEEE, 2008.
 A.Khan, B.Baharudin, K.khan, â€œSentence Based Sentiment Classification from Online Customer Reviewsâ€, Frontiers of information Technology, ACM, 2010.
 N.Aleebrahim, M.Fathian and M.Reza Gholamian, â€œSentiment Classification of Online Product Reviews Using Product Featuresâ€, Data Mining and Intelligent Information Technology Applications, pp. 242 â€“ 245, IEEE, 2010.
 K. Gayathri, A. Marimuthu, â€œText Document Pre-Processing with the KNN for Classification Using the SVMâ€, Intelligent Systems and Control, pp. 453 â€“ 457, IEEE, 2012.
 X.Hu and B.Wu, â€œClassification and Summarization of Pros and Cons for Customer Reviewsâ€, Web Intelligence and Intelligent Agent Technologies, Vol. 3, pp. 73 â€“ 76, IEEE, 2009.
 Jack V.Tu et.al Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes, Journal of Clinical Epidemiology, Volume 49, Issue 11, November 1996, Pages 1225-1231, https://doi.org/10.1016/S0895-4356(96)00002-9.
 A.Sharma and S.Dey, â€œA Document-Level Sentiment Analysis Approach Using Artificial Neural Network and Sentiment Lexiconsâ€, ACM SIGAPP Applied Computing Review, VOL. 12, pp. 67-75, ACM, 2012.
 Jurgen Schmidhuber et.al, Deep Learning in Neural Networks: An Overview (NPTL)
 Yang, D, Chen, G., Wang, and H. et al. Learning vector quantization neural network method for network intrusion detection Wuhan Univ. J. of Nat. Sci. (2007) 12: 147. https://doi.org/10.1007/s11859-006-0258-z.
 Elman, Jeffrey L. (1990).â€Finding structure in time." Cognitive Science, 14, pp. 179-211. https://doi.org/10.1207/s15516709cog1402_1.
 Fausett, Laurene. (1994). Fundamentals of neural networks: Architectures, algorithms, and applications. New Jersey: Prentice Hall.
 Cruse, Holk; Neural Networks as Cybernetic Systems, 2nd and revised edition
 McCulloch, W.Pitts, W. â€œA logical calculus of the ideas immanent in nervous activityâ€, The Bulletin of Mathematical Biophysics, Volume 5, pp.115-133, 1943. https://doi.org/10.1007/BF02478259.
 Rosenblatt, Frant, â€œThe Perceptron: A probabilistic Model for Information Storage and Organization in the Brainâ€, Cornell Aeronautical Laboratory, Psychological Review, volume 65, No. 6, pp. 386-408, 1958.
 Mu-Song Chen, M.T. Manry, â€œPower Series Analyses of Back-Propagation Neural Networksâ€, International Joint Conference on Neural Networks, Volume I, pp 295-300, 1991.
 Mu-Song Chen, M.T. Manry, â€œNonlinear Modeling of Back-Propagation Neural Networksâ€, International Joint Conference on Neural Networks, Volume II, pp 899, 1991.
 Peter D. Turney, â€œThumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviewsâ€, Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 471-424, 2002.
 Shikha Chourasia â€œSurvey paper on improved methods of ID3 decision tree classificationâ€ International Journal of Scientific and Research Publications, Volume 3, Issue 12, December 2013
 Muharram M.A., Smith G.D. (2004) Evolutionary Feature Construction Using Information Gain and Gini Index. In: Keijzer M., Oâ€™Reilly UM., Lucas S., Costa E., Soule T. (eds) Genetic Programming. EuroGP 2004. Lecture Notes in Computer Science, vol 3003. Springer, Berlin, Heidelberg.
 Decision Tree Algorithm. In: Khachidze V., Wang T., Siddiqui S., Liu V., Cappuccio S., Lim A. (eds) Contemporary Research on E-business Technology and Strategy. iCETS 2012. Communications in Computer and Information Science, vol 332. Springer, Berlin, Heidelberg.
 He Zhang, Runjing Zhou, The analysis and optimization of decision tree based on ID3 algorithm, 2017 9th International Conference on Modelling, Identification and Control (ICMIC).