Loading...
Paper Type
ERF
Abstract
The popularity and pervasiveness of social media platforms as mechanisms for the rapid dissemination and propagation of news and the ease by which such information can be created and shared, makes it increasingly important to verify its credibility. This work focuses on the automatic credibility analysis of news on microblogging platforms such as Twitter. Using the publicly available PHEME twitter dataset, we perform classification using the Long Short-Term Memory (LSTM) technique. Our dataset was divided into two parts, 80% for training and validation, and 20% for testing. The preliminary results show the potential of our proposed model to classify news tweets as credible (or non-credible) based on tagging and textual features.
Recommended Citation
Vyas, Piyush and El-Gayar, Omar, "Credibility Analysis of News on Twitter using LSTM: An exploratory study" (2020). AMCIS 2020 Proceedings. 17.
https://aisel.aisnet.org/amcis2020/social_computing/social_computing/17
Credibility Analysis of News on Twitter using LSTM: An exploratory study
The popularity and pervasiveness of social media platforms as mechanisms for the rapid dissemination and propagation of news and the ease by which such information can be created and shared, makes it increasingly important to verify its credibility. This work focuses on the automatic credibility analysis of news on microblogging platforms such as Twitter. Using the publicly available PHEME twitter dataset, we perform classification using the Long Short-Term Memory (LSTM) technique. Our dataset was divided into two parts, 80% for training and validation, and 20% for testing. The preliminary results show the potential of our proposed model to classify news tweets as credible (or non-credible) based on tagging and textual features.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.