Skip to Main content Skip to Navigation
New interface
Conference papers

Machine Learning Approach to Analyze and Predict the Popularity of Tweets with Images

Abstract : Social Media platforms play a major role in spreading information. Twitter, is one such platform which is used by millions of people to share information every day. Twitter with the recent introduction of a feature that helps its users to attach images to a tweet has changed the dynamics of tweeting. Many people now prefer to tweet with images. This study tries to analyse and predict the popularity of such tweets. This study uses learning mechanisms like decision tree, neural networks and random forests to learn the tweets posted by people with a higher number of followers. Image parameters, network variables, transactional, and historical variables of a tweet are identified and are trained for predicting the test data. This study can help businesses to build better social media tools, which allows customers to tweet data at the right time. This study also identifies the contribution of various parameters that may help a tweet to go viral.
Complete list of metadata

Cited literature [19 references]  Display  Hide  Download
Contributor : Hal Ifip Connect in order to contact the contributor
Submitted on : Thursday, August 29, 2019 - 3:39:24 PM
Last modification on : Friday, August 30, 2019 - 10:10:25 AM


Files produced by the author(s)


Distributed under a Creative Commons Attribution 4.0 International License



Nimish Joseph, Amir Sultan, Arpan Kumar Kar, P. Vigneswara Ilavarasan. Machine Learning Approach to Analyze and Predict the Popularity of Tweets with Images. 17th Conference on e-Business, e-Services and e-Society (I3E), Oct 2018, Kuwait City, Kuwait. pp.567-576, ⟨10.1007/978-3-030-02131-3_49⟩. ⟨hal-02274178⟩



Record views


Files downloads