Attention Based Neural Architecture For Rumor Detection With Author Context Awareness
Keywords
Attention; Context; Deep Neural Network; Rumor Detection; Social Network
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.
Publication Date
9-1-2018
Publication Title
2018 13th International Conference on Digital Information Management, ICDIM 2018
Number of Pages
82-87
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/ICDIM.2018.8847052
Copyright Status
Unknown
Socpus ID
85073503720 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85073503720
STARS Citation
Tarnpradab, Sansiri and Hua, Kien A., "Attention Based Neural Architecture For Rumor Detection With Author Context Awareness" (2018). Scopus Export 2015-2019. 10573.
https://stars.library.ucf.edu/scopus2015/10573