Literature Survey: Data-driven Approach for Selection of an Ensemble Model of Profane Words Detection in Social Media

Abstract / Description

This paper presents a literature survey on data-driven approaches for selecting an ensemble model for detecting profane words in social media. The study was motivated by the increasing use of profanity and abusive language in online platforms, where existing profanity filters often fail due to evolving language patterns employed by cyberbullies. The survey reviews current approaches to profanity detection, focusing on machine learning and ensemble techniques that improve the accuracy, reliability, and adaptability of automated content moderation systems. The study contributes to the advancement of intelligent social media monitoring and cyberbullying prevention through data-driven natural language processing techniques.

Keywords

Suggested Citation