Finding Social Media Trolls: Dynamic Keyword Selection Methods for Rapidly-Evolving Online Debates
Abstract
Online harassment is a significant social problem. Prevention of online harassment requires rapid detection of harassing, offensive, and negative social media posts. In this paper, we propose the use of word embedding models to identify offensive and harassing social media messages in two aspects: detecting fast-changing topics for more effective data collection and representing word semantics in different domains. We demonstrate with preliminary results that using the GloVe (Global Vectors for Word Representation) model facilitates the discovery of new and relevant keywords to use for data collection and trolling detection. Our paper concludes with a discussion of a research agenda to further develop and test word embedding models for identification of social media harassment and trolling.
Additional Information
Alvarez thanks the John Randolph Haynes and Dora Haynes for supporting his research in this area. Prof. Anandkumar is supported by Bren endowed Chair, faculty awards from Microsoft, Google, and Adobe, DARPA PAI and LwLL grants. Anqi Liu is a PIMCO postdoctoral fellow at Caltech. Codes Repository: The codes used for generating results in this paper can be accessed from the link: https://github.com/mayasrikanth/TwitterStudiesCode.Attached Files
Submitted - 1911.05332.pdf
Files
| Name | Size | Download all |
|---|---|---|
|
md5:c81b8acd8ba928ba9e9d4f0c683ecc7b
|
209.5 kB | Preview Download |
Additional details
- Eprint ID
- 100567
- Resolver ID
- CaltechAUTHORS:20200108-154406622
- Bren Professor of Computing and Mathematical Sciences
- Microsoft
- Adobe
- Defense Advanced Research Projects Agency (DARPA)
- Caltech PIMCO Graduate Fellowship
- Created
-
2020-01-08Created from EPrint's datestamp field
- Updated
-
2023-06-02Created from EPrint's last_modified field