Detecting Sensitive Content in Tweets using Hybrid Recurrent Neural Networks

Sharma, Vishwadeep (2023) Detecting Sensitive Content in Tweets using Hybrid Recurrent Neural Networks. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (468kB) | Preview
Preview	PDF (Configuration Manual) Download (384kB) | Preview

Abstract

This comprehensive report addresses the intricate task of sensitive word detection in tweets originating from Pakistan, employing a meticulously crafted methodology. The research explores stacked LSTM-GRU architectures, individual LSTM, and GRU models, investigating various hyperparameter configurations to discern their impact on the model's performance in sequence modeling tasks. The evaluation of different architectural choices reveals that a model with a larger embedding dimension of 100, coupled with LSTM units of 50 and GRU units of 50, demonstrates promising outcomes, achieving a test accuracy of approximately 56%. By providing detailed examination of sequence modeling methods & possible future study directions, paper provides helpful insights in difficulties & possibilities of identifying sensitive material into social media.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Milosavljevic, Vladimir UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4150 Computer Network Resources > The Internet > World Wide Web > Websites > Online social networks T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > The Internet > World Wide Web > Websites > Online social networks
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	22 May 2025 15:52
Last Modified:	22 May 2025 15:52
URI:	https://norma.ncirl.ie/id/eprint/7609

Actions (login required)

View Item