TechRxiv
farmer paper IEEE transaction.pdf (1.13 MB)
Download file

Predicting Democratic Protests Paradigm from Twitter : Using Deep learning BiLSTM Model

Download (1.13 MB)
preprint
posted on 11.02.2022, 17:46 authored by Rhea MahajanRhea Mahajan

Twitter allows its users to share their concerns, ideas and daily activities online. This shared content by individuals provides a rich source of natural occurring data. The rapidity and flexibility of tweets have motivated its use as a tool for mobilizing masses for organizing strikes, protests, and other demonstrations. In this paper, we hypothesized that unrestricted data available on Twitter has potential power to predict day and location of major protests when deep learning and data mining is applied to its unstructured data. The prediction model used in the study is Bidirectional Long Short Term Memory (BiLSTM) Model. The results of our experiment shows that our model performs better than existing baselines models achieving an accuracy of 82.02% on testing data and 95.28% on training data. Overall, the aim of the paper is to study the efficacy of data mining techniques on publicly available data on Twitter in predicting mass protests and demonstrations.

History

Email Address of Submitting Author

rhea4788@gmail.com

Submitting Author's Institution

UNiversity of Jammu

Submitting Author's Country

India

Usage metrics

Licence

Exports