- 129 views
- 301 downloads
A deep learning based multilingual hate speech detection for resource scarce languages
-
- Author(s) / Creator(s)
-
Over the last decade, the increased use of social media has led to an increase in hateful activities in social networks. An international issue that weakens the cohesiveness of civil societies is hate speech on internet social networks. Due to the lack of restrictions set by these sites for its users to express their views as they like. Hate speech is one of the most dangerous of these activities, so users have to protect themselves from these activities from social media sites such as YouTube, Facebook, Twitter, etc. Large-scale social platforms are currently investing important resources into automatically detecting and classifying hateful content, without much success.this research introduces a method for using deep learning algorithms to predict hate speech from social media websites. We implement proposed algorithms to detect hate speech in five different language: Arabic, English, and Urdu. this study employs a variety of feature engineering techniques and a comparative study among different machine and deep learning algorithms to automatically detect hate speech messages on many datasets. after hate speech data is collected, as a part of the preprocessing steaming, token splitting, character removal, and inflection elimination are carried out before performing the hate speech recognition process through deep learning algorithms. In the future, we would like to deploy proposed algorithms to other low resource languages and explore more language specific features in deep learning framework.
-
- Date created
- 2022
-
- Type of Item
- Research Material