Advertisement

Label Assignment and Sentimental Analysis for a Product Review on Twitter Data

  • Chandra Prakash Singh Sengar
  • S. Jaya Nirmala
Conference paper
  • 17 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1118)

Abstract

The most popular microblogging social media is Twitter, where people express their point of view toward different things. They bought different products and give their unbiased opinion on Twitter. In this paper, a novel method is proposed to get the opinions of customers toward the product or company and analyze it. The product-related Tweets are gathered by Twitter with the help of the browser. This method is not using Twitter API. The proposed methods are defined for labeling Tweets in three emotions, that is, positive, negative, and neutral efficiently. Sentiment analysis models are used for classifying the opinions of the customer toward that product and toward individual features of the product. Using these results, it improves the future versions of the product. This research technique helps and improves the marketing approaches and high selling of product as well. It predicts the best and worst feature of the product with respect to customer opinion with an accuracy of 93.62%.

Keywords

Label assignment Sentiment analysis Product review Twitter data Classification algorithms 

References

  1. 1.
  2. 2.
  3. 3.
  4. 4.
  5. 5.
    Jose, A.K., Bhatia, N., Krishna, S.: Twitter Sentiment Analysis. National Institute of Technology Calicut (2010)Google Scholar
  6. 6.
    Tang, Q., Gu, B., Whinston, A.B.: Content contribution in social media: the case of YouTube. In: The 2nd Conference of Social Media. Maui, Hawaii (2012)Google Scholar
  7. 7.
    Scrip wrote in python, that bypass some to the limitation of Twitter API on getting Tweets, which is older than a week as well. https://github.com/Jefferson-Henrique/GetOldTweets-python
  8. 8.
  9. 9.
    De Smedt, T., Nijs, L., Daelemans, W.: Creative Web Services with Pattern (2013)Google Scholar
  10. 10.
    Breen, J.: Positive Word List and Negative Word List. https://github.com/jeffreybreen
  11. 11.
    Osimo, D., Mureddu, F.: Research challenge on opinion mining and sentiment analysis. In: Proceeding of the 12th Conference of Fruct Association, UK (2010)Google Scholar
  12. 12.
    Pak, A., Paroubek, P.: Twitter as a corpus for sentiment analysis and opinion mining. In: Special Issue of International Journal of Computer Application. Universite de Paris-Sud, France (2010)Google Scholar
  13. 13.
    Ranjan, S., Sood, S., Verma, V.: Twitter sentiment analysis of real-time customer experience feedback for predicting growth of ındian telecom companies. In: 2018 4th International Conference on Computing Sciences (ICCS), Jalandhar, pp. 166–174 (2018).  https://doi.org/10.1109/iccs.2018.00035
  14. 14.
    Sharma, P., Moh, T.: Prediction of Indian election using sentiment analysis on Hindi Twitter. In: 2016 IEEE International Conference on Big Data (Big Data), Washington, DC, pp. 1966–1971 (2016).  https://doi.org/10.1109/bigdata.2016.7840818, http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7840818&isnumber=7840573
  15. 15.
    Text Blob: Simplified Text Processing. https://textblob.readthedocs.io/en/dev/
  16. 16.
    Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E.: Scikit-Learn. 12(Oct):2825 − 2830 (2011)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Chandra Prakash Singh Sengar
    • 1
  • S. Jaya Nirmala
    • 1
  1. 1.Department of Computer Science and EngineeringNational Institute of Technology TiruchirappalliTiruchirappalliIndia

Personalised recommendations