Towards improving performance of tweet sentiment analysis by optimized feature weight using metaheuristic discriminative classifier approach
Keywords:Sentiment analysis, feature optimization, ACO, PSO, NaÃ¯ve Bayes, BAT.
Technology is exponentially rising day by day and one of the most booming product of this gradually updated technology is social media. Social media has become that platform where user can share his experience or views and can communicate to a mass in a single instance. Expanding technology has allowed the user to post its views anytime and from anywhere. These posted views can be made useful by the companies for their product reviews and this is the reason new fields like Sentiment analysis, Text mining have come into existence. Challenge in text mining is extraction of weight given to features because features weights is highly sparse in nature which increase the false positive rate and reducing the accuracy. In this paper proposed Optimized Feature Sentiment Classifier (OFSC) System gives the optimized weight by convergence of error or minimizing error. After that we improve the learning through classifier. Proposed approach focus on hybridization of optimization techniques ACO, PSO and BAT with NaÃ¯ve Bayes Classifier to enhance the parametric values of performance matrix. In our work we have taken Twitter data as a sample dataset for optimized feature classification.
 Nadia F. F. da Silva, Eduardo R. Hruschka,Estevam R. et.al. â€œTweet Sentiment Analysis with Classifier Ensemblesâ€ july16-2014. https://doi.org/10.1016/j.dss.2014.07.003.
 Al-Jarrah, Omar Y., et al. "Efficient machine learning for big data: A review." Big Data Research 2.3 (2015): 87-93. https://doi.org/10.1016/j.bdr.2015.04.001.
 Yu, Yang, and Xiao Wang. "World Cup 2014 in the Twitter World: A big data analysis of sentiments in US sports fansâ€™ tweets." Computers in Human Behavior 48 (2015): 392-400. https://doi.org/10.1016/j.chb.2015.01.075.
 Colleoni, Elanor, Alessandro Rozza, and Adam Arvidsson. "Echo chamber or public sphere? Predicting political orientation and measuring political homophily in Twitter using big data." Journal of Communication 64.2 (2014): 317-332. https://doi.org/10.1111/jcom.12084.
 Wang, Wenbo et al. "Harnessing twitter" big data" for automatic emotion identification." Privacy, Security, Risk and Trust (PASSAT), 2012 International Conference on and 2012 International Confernece on Social Computing (SocialCom). IEEE, 2012. https://doi.org/10.1109/SocialCom-PASSAT.2012.119.
 Lin, Jimmy, and DmitriyRyaboy. "Scaling big data mining infrastructure: the twitter experience." ACM SIGKDD Explorations Newsletter 14.2 (2013): 6-19. https://doi.org/10.1145/2481244.2481247.
 Mishne, Gilad, et al. "Fast data in the era of big data: Twitter's real-time related query suggestion architecture." Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data. ACM, 2013. https://doi.org/10.1145/2463676.2465290.
 Sumbaly, Roshan, Jay Kreps, and Sam Shah. "The big data ecosystem at linkedin." Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data. ACM, 2013. https://doi.org/10.1145/2463676.2463707.
 Compton, Ryan, et al. "Detecting future social unrest in unprocessed twitter data:â€œemerging phenomena and big dataâ€." Intelligence and Security Informatics (ISI), 2013 IEEE International Conference On. IEEE, 2013. https://doi.org/10.1109/ISI.2013.6578786.
 Goonetilleke, Oshini, et al. "Twitter analytics: a big data management perspective." ACM SIGKDD Explorations Newsletter 16.1 (2014): 11-20. https://doi.org/10.1145/2674026.2674029.
 David Zimbra et.al. â€œBrand-Related Twitter Sentiment Analysis using Feature Engineering and the Dynamic Architecture for Artificial Neural Networksâ€1530-1605/16 $31.00 Â© 2016 IEEEDOI 10.1109/HICSS.2016.244.
 RabiNarayanBehera et.al. â€œEnsemble based Hybrid Machine LearningApproach for Sentiment Classification- AReviewâ€International Journal of Computer Applications (0975â€“8887)Volume 146 â€“No.6, July 2016 https://doi.org/10.5120/ijca2016910813.
 Alexander Pak,Patrick Proubek â€œTwitter as a Corpus for Sentiment Analysis and Opinion Miningâ€.
 Andres Montoyo,Patricio Martienzâ€œSubjectivity and sentiment analysis: An overview of the current state of the area and envisaged developmentsâ€ https://doi.org/10.1016/j.dss.2012.05.022.
 Yang Yu,Wenjing Duan et.al.â€œThe impact of social and conventional media on firm equity value: A sentiment analysis approachâ€ https://doi.org/10.1016/j.dss.2012.12.028.
 Walaa Medhat,Ahmed Hassanâ€œSentiment analysis algorithms and applications: A surveyâ€ https://doi.org/10.1016/j.asej.2014.04.011.
 Stuti Mehla, Saurabh Upadhyay â€œPerformance Comparison of Statistical Techniques with Big Data Analysisâ€ International Journal of Computer Applications (0975 â€“ 8887) Volume 169 â€“ No.6, July 2017 https://doi.org/10.5120/ijca2017914770.
 Mohammed Hossein, Barkhordaril,Mahdi Nimanesh1â€œScaDiPaSi: An Effective Scalable and Distributable MapReduce - Based Method to Find Patient Similarityon Huge Healthcare Networks Copyright Â© 2015 Elsevier Inc. https://doi.org/10.1016/j.bdr.2015.02.004.
 Tao Huangb, Liang Lanc et.al.â€œPromises and Challenges of Big Data Computing in Health Sciencesâ€ Copyright Â© 2015 Elsevier Inc.
 Xiaolong Jina, Benjamin W.Waha et.al.â€œSignificance and Challenges of Big Data Researchâ€Copy right Â© 2015 Elsevier Inc.
 Raymond YK Laub,J Leon Zhaob et.al.â€œDemystifying Big Data Analytic for Business Intelligenceâ€ Copyright Â© 2015Elsevier Inc.
 Ibrahim Abaker Targio Hashema, Ibrar Yaqooba et.al.â€œThe rise of â€œbig dataâ€ on cloud computing: Review and open research issuesâ€Copyright Â© 2014Elsevier Ltd.
 Wullianallur Raghupathi and Viju Raghupathi â€œBig data analytics in healthcare: promise and potentialâ€ Raghupathi and Raghupathi Health Information Science and Systems 2014, 2:3 http://www.hissjournal.com/content/2/1/3. https://doi.org/10.1186/2047-2501-2-3.