Twitter Rumour Detection using Temporal Property of Tweets

Parab, Nikita Nitin (2019) Twitter Rumour Detection using Temporal Property of Tweets. Masters thesis, Dublin, National College of Ireland.

Preview

PDF (Master of Science) Download (1MB) | Preview

Abstract

There are mainly two type of rumours on social media, it can be disinformation or misinformation. While disinformation is intentional and spread to divert people from truth, misinformation is unintentional news which turns out to be false. Either ways, it causes panic and needs to be identified as quickly as possible to avoid further chaos. This research paper presents a method for detecting rumour in the first hour the tweet was posted. The social media platform used for this project is twitter due to its popularity. This research is implemented on 7 events which have different propagation patterns. The feature used for this project is timestamp of the tweets and its reactions. The models implemented include Gaussian Naive Bayes, Support Vector Machine, Random Forest, Classification and Regression Trees, K Nearest Neighbours and Deep Learning. All these models are implemented to study how they perform for different propagation patterns. Overall, it can be seen that most of the models work best with events that have well defined pattern and work poor iffthe events have less samples or do not have defined patterns. The highest accuracy recorded of 78% was for Charlie Hebdo event for both CART and SVM models. The lowest accuracy of 19% was for Gurlitt event after implementing Deep Learning Model.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4150 Computer Network Resources > The Internet > World Wide Web > Websites > Online social networks T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > The Internet > World Wide Web > Websites > Online social networks
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Caoimhe Ní Mhaicín
Date Deposited:	11 Oct 2019 15:10
Last Modified:	11 Oct 2019 15:10
URI:	https://norma.ncirl.ie/id/eprint/3852

Actions (login required)

View Item