Predicting Future with Social Media Based on Sentiment and Quantitative Analysis

  • Sahil SharmaEmail author
  • Jon Rokne
  • Reda Alhajj
Part of the Lecture Notes in Social Networks book series (LNSN)


With the advent and spread of Web 2.0 (O’Reilly, 2005) in the early twenty-first century, the Internet has seen a big shift in the participation and proportional quantity content coming from the average Internet users. Among the various aspects of Internet that came into existence owing to this large flow of user-generated content, the social media platforms are one of the most prominent ones. These sites are highly popular and host home to big virtual communities. With the rising popularity, these sites now comprise of a vast proportion of people reflecting their real-world opinions and emotions in a virtual setup. Now, social media is a virtual data log of human interactions. These platforms serve very big quantity of data which has intrinsic insights into the user’s perspective on different aspects. Hence, for modern-day research purposes, this informational data comprises of large potentials. Many of such researches include the research to predict future in stock markets and there are various examples of how social data can be used to benefit—even totally automate the process of stock trading, using social media to form early warning system for disaster management and emergencies, etc. One such interesting is to analyze and see whether social media insights can help us predict the outcomes of an election. In this research, we try to focus on the 2016 US presidential elections and do a case study between the few leading candidates and see whether the analysis can help us predict the winner. This analysis is carried out on the social media site, Twitter. This research is feasible since the topic under consideration is heavily human-influenced. It makes sense that we should be feasible to use social media as an efficient indicator of probable electoral outcomes since a large proportion of population are active on these social media platforms and do share their opinions. The opinions reflect their real-world perspective on these sensitive topics. Hence, it can be expected to translate to real-world outcomes of such events.


Sentiment analysis Social media Election Twitter Natural language processing Data analysis Data crawling Prediction 


  1. 1.
    O’Reilly, Tim (2005). What is web 2.0.Google Scholar
  2. 2.
    Gaurav, M., Srivastava, A., Kumar, A., & Miller, S. (2013). Leveraging candidate popularity on Twitter to predict election outcome. In Proceedings of the 7th Workshop on Social Network Mining and Analysis. ACM.Google Scholar
  3. 3.
    Cameron, M. P., Barrett, P., & Stewardson, B. (2016). Can social media predict election results? Evidence from New Zealand. Journal of Political Marketing, 15(4), 416–432.CrossRefGoogle Scholar
  4. 4.
    Khatua, A., Khatua, A., Ghosh, K., & Chaki, N. (2015). Can# Twitter_Trends Predict Election Results? Evidence from 2014 Indian General Election. In System Sciences (HICSS), 2015 48th Hawaii International Conference on. Kauai, HI: IEEE.Google Scholar
  5. 5.
    Wang, H., Can, D., Kazemzadeh, A., Bar, F., & Narayanan, S. (2012). A system for real-time twitter sentiment analysis of 2012 us presidential election cycle. In Proceedings of the ACL 2012 System Demonstrations. Association for Computational Linguistics.Google Scholar
  6. 6.
    Ceron, A., Curini, L., Iacus, S. M., & Porro, G. (2014). Every tweet counts? How sentiment analysis of social media can improve our knowledge of citizens’ political preferences with an application to Italy and France. New Media & Society, 16(2), 340–358.CrossRefGoogle Scholar
  7. 7.
    Bermingham, A., & Smeaton, A. (2011). On using Twitter to monitor political sentiment and predict election results. In Proceedings of the Workshop on Sentiment Analysis where AI meets Psychology (SAAIP 2011).Google Scholar
  8. 8.
    Almuhimedi, H., Wilson, S., Liu, B., Sadeh, N., & Acquisti, A. (2013). Tweets are forever: a large-scale quantitative analysis of deleted tweets. In Proceedings of the 2013 Conference on Computer Supported Cooperative Work. ACM.Google Scholar
  9. 9.
    Lu, R., Xu, Z., Zhang, Y., & Yang, Q. (2012). Trends predicting of topics on twitter based on MACD. IACSIT 12: 44-49Google Scholar
  10. 10.
    Qi, J., Qu, Q., & Tan, Y (2012). Topic evolution prediction of user generated contents considering enterprise generated contents. In Proceedings of the First ACM International Workshop on Hot Topics on Interdisciplinary Social Networks Research. ACM.Google Scholar
  11. 11.
    Liu, W., Deng, Z.-H., Gong, X., Jiang, F., & Tsang, I. W. et al. (2015). Effectively predicting whether and when a topic will become prevalent in a social network. In Twenty-Ninth AAAI Conference on Artificial Intelligence.Google Scholar
  12. 12.
    Asur, Sitaram, and Huberman, B.A. (2010). Predicting the future with social media. In Web Intelligence and Intelligent Agent Technology (WI-IAT), 2010 IEEE/WIC/ACM International Conference on (Vol. 1). Toronto, AB, Canada: IEEE.Google Scholar
  13. 13.
    Nguyen, L. T., Wu, P., Chan, W., Peng, W., & Zhang, Y. (2012). Predicting collective sentiment dynamics from time-series social media. In Proceedings of the First International Workshop on Issues of Sentiment Discovery and Opinion Mining. ACM.Google Scholar
  14. 14.
    Mulay, S. A., Joshi, S. J., Shaha, M. R., Vibhute, H. V., & Panaskar, M. P. (2016). Sentiment analysis and opinion mining with social networking for predicting box office collection of movie. International Journal of Emerging Research in Management & Technology, 5, 74–79.Google Scholar
  15. 15.
    Gayo-Avello, D. (2012). “I wanted to predict elections with Twitter and all I got was this Lousy paper”—A balanced survey on election prediction using Twitter data. arXiv preprint arXiv:1204.6441.Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of CalgaryCalgaryCanada

Personalised recommendations