Attention Based Neural Architecture for Rumor Detection with Author Context Awareness

TL;DR

This paper introduces an ensemble neural network that uses word attention and author context to improve rumor detection accuracy on Twitter, addressing limitations of previous methods that ignored broader contextual cues.

Contribution

It proposes a novel architecture combining word attention and author context to enhance rumor classification performance on social media data.

Findings

Achieved improved accuracy over baseline models

Utilized author style and characteristics as additional context

Demonstrated effectiveness on real-world Twitter datasets

Abstract

The prevalence of social media has made information sharing possible across the globe. The downside, unfortunately, is the wide spread of misinformation. Methods applied in most previous rumor classifiers give an equal weight, or attention, to words in the microblog, and do not take the context beyond microblog contents into account; therefore, the accuracy becomes plateaued. In this research, we propose an ensemble neural architecture to detect rumor on Twitter. The architecture incorporates word attention and context from the author to enhance the classification performance. In particular, the word-level attention mechanism enables the architecture to put more emphasis on important words when constructing the text representation. To derive further context, microblog posts composed by individual authors are exploited since they can reflect style and characteristics in spreading information, which are significant cues to help classify whether the shared content is rumor or legitimate news. The experiment on the real-world Twitter dataset collected from two well-known rumor tracking websites demonstrates promising results.