Towards Addressing Identity Deception in Social Media using Bangla Text-Based Gender Identification

Authors: Sultan Ahmed, Md Jahangir Alam, Sajedul Talukder, Ismail Hossain

Paper

Abstract

Gender identification from social media content can play a crucial role in detecting and mitigating the risks posed by counterfeit accounts. Authentic gender representation can foster a safer and more diverse online environment. While research has been conducted on gender identification in languages such as English, Russian, and Arabic, there remains a gap in studies targeting Bangla and its related languages. This paper introduces a stylometric feature approach to discern the gender of authors from Bangla texts. Utilizing a dataset of 5,000 posts sourced from various Facebook groups, we trained seven traditional machine learning models. Among these, the Random Forest (RF) model notably excelled, achieving an accuracy of 73.37% and an F1-Score of 79.25%, thus setting a promising benchmark in gender identification from Bangla texts.

Key Contributions

• Placeholder — to be added.

Resources

Placeholder — code, data, slides, and figures to be added.

BibTeX

@inproceedings{ahmed2023towards,
  title     = {Towards Addressing Identity Deception in Social Media using Bangla Text-Based Gender Identification},
  author    = {Ahmed, Sultan and Alam, Md Jahangir and Talukder, Sajedul and Hossain, Ismail},
  booktitle = {ASONAM 2023},
  year      = {2023},
  url       = {https://doi.org/10.1145/3625007.3627732}
}