Modeling Hate Speech Detection in Social Media Interactions Using Bert

Gibran Mwadime, Moses Odeo, Boniface Ngari and Stephen Mutuvi
Additional contact information
Gibran Mwadime: Department of Computer Science, Multimedia University of Kenya
Moses Odeo: Department of Computer Science, Multimedia University of Kenya
Boniface Ngari: Department of Computer Science, Multimedia University of Kenya
Stephen Mutuvi: Department of Computer Science, Multimedia University of Kenya

International Journal of Research and Scientific Innovation, 2020, vol. 7, issue 2, 62-65

Abstract: Hate speech propagation in social media sites has been happening over time and there is need to accurately identify and counter it so that those offended can seek redress and offenders can be punished for perpetrating the vice. In this paper, we demonstrate how fine tuning a pre-trained Google Bidirectional Encoder Representation from Transformers (BERT) model has been used to achieve an improvement in accuracy of classification of tweets as either hate speech or not. Random forests and logistic regression algorithms have been used to build baseline models with a publicly available twitter dataset from hatebase.org. To validate the BERT model, we collected data using Tweepy API and combined with data from hatebase.org for training. The results obtained show an improvement in accuracy of tweets classification as either hate speech or not from the baseline models by 7.22%.

Date: 2020
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.rsisinternational.org/journals/ijrsi/d ... -7-issue-2/62-65.pdf (application/pdf)
https://www.rsisinternational.org/virtual-library/ ... t&utm_campaign=First (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bjc:journl:v:7:y:2020:i:2:p:62-65

Access Statistics for this article

International Journal of Research and Scientific Innovation is currently edited by Dr. Renu Malsaria

More articles in International Journal of Research and Scientific Innovation from International Journal of Research and Scientific Innovation (IJRSI)
Bibliographic data for series maintained by Dr. Renu Malsaria ().