A Methodology for Processing Opinion Mining on GST in India from Social Media Data Using Recursive Neural Networks and Maximum Entropy Techniques

  • N. V. Muthu LakshmiEmail author
  • T. Lakshmi Praveena
Part of the SpringerBriefs in Applied Sciences and Technology book series (BRIEFSAPPLSCIENCES)


Online social media is ever growing area in our society and is becoming a part of human life. Most of the web users are interested to use publish and share information on social media. This paper proposed a methodology for processing opinion mining on Goods and Services Tax (GST) data which is posted in social media using Recursive Neural Networks and Maximum Entropy techniques. GST is an indirect tax and was introduced by Indian government on 1st July 2017. This methodology predicts the effect of GST implementation in India based on data collected from Face book and Twitter web sites. Naïve Bayes, Simple Vector Machine and decision trees are simple in implementations but don’t allow multi class problems and rich hypothesis whereas Recursive Neural Networks improves the performance based on correlation and dependencies between variables. Maximum Entropy is also an efficient technique to estimate probability distribution and to deal with dependent attributes. The proposed methodology determines positive and negative impact on different types of people and finds opinion polarity to specify priority of opinions.


Preprocessing Opinion mining Social media data Recursive neural networks (RNN) Maximum entropy (ME) 


  1. 1.
    Stieglitz S, Dang-Xuan L, Bruns A, Neuberger C (2014) Socialmedia analytics an interdisciplinary approach and its implications for information systems. Scholar
  2. 2.
    Narwani M, Lulla S, Bhatia V, Hemwani R, Bhatia G (2016) Social media analytics for E-commerce organisations. Int J Comput Sci Inf Technol 7(6):2431–2435Google Scholar
  3. 3.
    Medhat Walaa, Hassan A, Korashy H (2014) Sentiment analysis algorithms and applications: a survey. Ain Shams Eng J 5:1093–1113CrossRefGoogle Scholar
  4. 4.
    Linga SC, Osmana A, Muhammada S, Yenga SK, Jinb LY (2015) Goods and services tax (GST) compliance among Malaysian consumers: the influence of price, government subsidies and income inequality. In: 7th international economics & business management conference, 5 & 6 Oct 2015 Google Scholar
  5. 5.
    Lakshmi praveena T, Muthu Lakshmi NV (2017) An overview of social media analytics. Int J Adv Sci Technol Eng Manage Sci (IJASTEMS-ISSN: 2454-356X) 3(1)Google Scholar
  6. 6.
    Devika MD, Sunitha C, Ganesha A (2016) Sentiment analysis: a comparative study on different approaches. In: Fourth international conference on recent trends in computer science & engineering, Chennai, Tamil Nadu, India, Procedia Computer Science 87:44–49Google Scholar
  7. 7.
    Verma JP, Agrawal S, Patel B, Patel A (2016) Big data analytics: challenges and applications for text, audio, video, and social media data. Int J Soft Comput Artif Intell Appl (ijscai) 5(1)CrossRefGoogle Scholar
  8. 8.
    Fan W, Gordon MD (2014) The power of social media analytics. Commun ACM 57. Scholar
  9. 9.
    Wu Y, Cao N, Gotz D, Tan Y-P, Keim DA (2016) A survey on visual analytics of social media data. J IEEE Trans Multimedia Arch 18(11):2135–2148CrossRefGoogle Scholar
  10. 10.
    Lassen NB, la Cour L, Vatrapu R (2016) Predictive analytics with social media dataGoogle Scholar
  11. 11.
  12. 12.
    Stieglitz S (2014) Social media and political communication—a social media analytics framework article. Scholar
  13. 13.
    Brauer C, Bernroider EWN (2015) Social media analytics with Facebook—the case of higher education institutions. In: International conference on HCI in business, HCIB 2015, pp 3–12Google Scholar
  14. 14.
    Bright J, Margetts H, Hale S, Yasseri T (2014) The use of social media for research and analysis: a feasibility study. A report of research carried out by the Oxford Internet Institute on behalf of the Department for Work and PensionsGoogle Scholar
  15. 15.
  16. 16.
  17. 17.
    Amarouche K, Benbrahim H, Kassou I (2015) Product opinion mining for competitive intelligence. In: The international conference on advanced wireless, information, and communication technologies (AWICT 2015)CrossRefGoogle Scholar
  18. 18.
    Gulla R, Shoaiba U, Rasheedb S, Abidb W, Zahoorb B (2016) Pre processing of Twitter’s data for opinion mining in political context. In: 20th international conference on knowledge based and intelligent information and engineering systems, KES2016, New York, 5–7 Sept 2016Google Scholar
  19. 19.
    Taboada M, Simon Fraser University, Brooke J, University of Toronto, Tofiloski M, Simon Fraser University, Voll K, University of British Columbia Manfred Stede, University of Potsdam, “Lexicon-Based methods for sentiment analysis”, published by Association For Computational LinguisticsGoogle Scholar
  20. 20.
  21. 21.
    Yuan Y, Zhou Y (2015) Twitter sentiment analysis with recursive neural networksGoogle Scholar
  22. 22.
    Patel D, Saxena S, Verma T (2016) Sentiment analysis using maximum entropy algorithm in big data. Int J Innov Res Sci Eng Technol (An ISO 3297: 2007 Certified Organization) 5(5)Google Scholar
  23. 23.
    Caruana R, Niculescu-Mizil A (2006) An empirical comparison of supervised learning algorithms. Department of Computer Science, Cornell University, Ithaca, NY 14853 USA Google Scholar
  24. 24.
    Deshmukh JS, Tripathy AK (2017) Entropy based classifier for cross-domain opinion mining. Volume 14, Issue 1, Appl Comput Inf, Science direct Google Scholar

Copyright information

© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Department of Computer ScienceSPMVVTirupatiIndia

Personalised recommendations