Effect of Demonetization on Stock Market Co-rrelated with Geo-Twitter Sentiment Analysis

  • Nabanita DasEmail author
  • Parikshit Ghosh
  • Debajyoti Roy
Conference paper
Part of the Learning and Analytics in Intelligent Systems book series (LAIS, volume 12)


In this modern age, social media platforms like Twitter plays a crucial role of sharing public opinions about any ongoing events in the form of sentiment, which may have direct impact on Stock Market movement. Twitter API do not allow more than 7 day’s historical data to be downloaded. In this paper, python language is used to collect historical data with Geo-Tagging for region-wise analysis. Here tweets are categorized by positive as 1, negative as −1 and neutral as 0. Here historical geo-tagged labelled tweets are collected using keywords and used to notice the impact on stock market during an event or after a specific event. Stock Market is very dynamic and complex area to be able to study. Since Stock Market data is time series data, we use ARIMA model to forecast the market movement. We then make a comparative study of the results of ARIMA of univariate and VAR of multivariate time series where extra variable is the sentiment score generated from the Twitter sentiment analysis.


Stock market prediction Sentiment analysis ARIMA model VAR model Regression Machine learning algorithms 


  1. 1.
    Aghababaei, S., Makrehchi, M.: Mining social media content for crime prediction. In: 2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI). IEEE (2016)Google Scholar
  2. 2.
    Zhou, F., et al.: Predicting topic participation by jointly learning user intrinsic and extrinsic preference. IEEE Access 7, 8917–8930 (2019)CrossRefGoogle Scholar
  3. 3.
    Lee, K., Agrawal, A., Choudhary, A.: Forecasting influenza levels using real-time social media streams. In: 2017 IEEE International Conference on Healthcare Informatics (ICHI). IEEE (2017)Google Scholar
  4. 4.
    Ali, M., Lu, L., Farid, M.: Detecting present events to predict future: detection and evolution of events on Twitter. In: 2018 IEEE Symposium on Service-Oriented System Engineering (SOSE). IEEE (2018)Google Scholar
  5. 5.
    Huang, C., Wang, D.: Demo paper: a confidence-aware truth estimation tool for social sensing applications. In: 2015 12th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON). IEEE (2015)Google Scholar
  6. 6.
    Chaniotakis, E., Antoniou, C., Pereira, F.C.: Enhancing resilience to disasters using social media. In: 2017 5th IEEE International Conference on Models and Technologies for Intelligent Transportation Systems (MT-ITS). IEEE (2017)Google Scholar
  7. 7.
    Hagras, M., Hassan, G., Farag, N.: Towards natural disasters detection from Twitter using topic modelling. In: 2017 European Conference on Electrical Engineering and Computer Science (EECS). IEEE (2017)Google Scholar
  8. 8.
    Tasoulis, S.K., et al.: Real time sentiment change detection of Twitter data streams. arXiv preprint arXiv:1804.00482 (2018)
  9. 9.
    Doraiswamy, H., et al.: A GPU-based index to support interactive spatio-temporal queries over historical data. In: 2016 IEEE 32nd International Conference on Data Engineering (ICDE). IEEE (2016)Google Scholar
  10. 10.
    Shekhar, H., Setty, S., Mudenagudi, U.: Vehicular traffic analysis from social media data. In: 2016 International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Computer Science and EngineeringTechno International New TownKolkataIndia

Personalised recommendations