Abstract
Online news media can serve as a very useful resource in terms of tracking the popularity and trend analyses of socio-political figures. The closest technology developed so far in this regard is Google Trends which is however based on the number of searches conducted by the users on the person or figure. And this is not necessarily a measure of popularity – the searches conducted could well be a random search. In this work, we define popularity (growing and diminishing) in terms of the sentiment scores received by the individual statements or sentences in the online news text with respect to some named-entity or socio-political figure. Based on the sentiment analysis and the named-entity extraction, we plot time-series line graphs that represent the popularity and trend analysis of the respective named-entities. The plots were verified with the help of individual opinion surveys and the conformance was more than 80% which signals that our proof-of-concept is viable and works. In the future, we will be extending the work to Nepali based on whatever has been achieved for English news media texts. We also will be improving the current individual module’s performances for English.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ceron, A., Curini, L., Iacus, S.M.: Tweet your vote: how content analysis of social networks can improve our knowledge of citizen’s policy preferences. An application to Italy and France. New Media Soc. 340–358 (2013)
Chan, H.P., King, I.: Thread popularity prediction and tracking with a permutation-invariant model. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 3392–3401. Association of Computational Linguistics, Brussels (2018)
Earl, J., Martin, A., McCarthy, J.D., Soule, S.A.: The use of newspaper data in the study of collective action. Ann. Rev. Soc. 65–80 (2004)
Giatsoglou, M., Vozalis, M.G., Diamantaras, K., Vakali, A., Sarigiannidis, G., Chtazisavvas, K.C.: Sentiment analysis leveraging emotions and word embeddings. Expert Syst. Appl. 214–224 (2017)
Gupta, N., Waykos, R.K., Narayanan, R., Chaudhari, A.: Introduction to machine prediction of personality from Facebook profiles. Int. J. Emerg. Technol. Adv. Eng. 66–70 (2017)
Hutto, C., Gilbert, E.: VADER: a parsimonious rule-based model for sentiment analysis of social media text. In: Proceedings of the Eighth International AAAI Conference on Weblogs and Social Media (2014)
Jain, V.K., Kumar, S.: Towards prediction of election outcomes using social media. Intell. Syst. Appl. 20–28 (2017)
Pang, B., Vaithyanathan, S.: Thumbs up? Sentiment classification using machine learning techniques. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 79–86. Association for Computational Linguistics, Philadelphia (2002)
Tatar, A., Antoniadis, P., DiasdeAmorim, M., Edida, S.: From popularity prediction to ranking online news. Soc. Netw. Anal. Min. 4, 174 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Bal, B.K., Regmi, S., Kafle, K. (2019). How Popular or Unpopular Have Your Leaders Been - Popularity Tracking and Trend Analysis of Socio-Political Figures. In: Kravets, A., Groumpos, P., Shcherbakov, M., Kultsova, M. (eds) Creativity in Intelligent Technologies and Data Science. CIT&DS 2019. Communications in Computer and Information Science, vol 1084. Springer, Cham. https://doi.org/10.1007/978-3-030-29750-3_25
Download citation
DOI: https://doi.org/10.1007/978-3-030-29750-3_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-29749-7
Online ISBN: 978-3-030-29750-3
eBook Packages: Computer ScienceComputer Science (R0)