Open Access

ARTICLE

Detection of Toxic Content on Social Networking Platforms Using Fine Tuned ULMFiT Model

by Hafsa Naveed¹, Abid Sohail², Jasni Mohamad Zain^3,*, Noman Saleem⁴, Rao Faizan Ali⁵, Shahid Anwar⁶

1 Department of Software Engineering, Faculty of Science, University of Lahore, Pakistan
2 Department of Computer Science, COMSATS University Islamabad, Lahore Campus, Pakistan
3 Institute for Big Data Analytics and Artificial Intelligence (IBDAAI), Kompleks Al-Khawarizmi, Universiti Teknologi MARA, 40450, Shah Alam, Selangor, Malaysia
4 TechnoGenics SMC PVT LTD, Lahore, Pakistan
5 Department of Computer and Information Science, Universiti Teknologi PETRONAS, Bandar Seri Iskandar, Tronoh, Perak, Malaysia
6 Department of Information Engineering Technology, National Skills University Islamabad, Sector H-8/1, Faiz Ahmed Faiz Road, Islamabad, Pakistan

* Corresponding Author: Jasni Mohamad Zain. Email:

Intelligent Automation & Soft Computing 2023, 35(1), 15-30. https://doi.org/10.32604/iasc.2023.023277

Received 01 September 2021; Accepted 19 January 2022; Issue published 06 June 2022

Abstract

Question and answer websites such as Quora, Stack Overflow, Yahoo Answers and Answer Bag are used by professionals. Multiple users post questions on these websites to get the answers from domain specific professionals. These websites are multilingual meaning they are available in many different languages. Current problem for these types of websites is to handle meaningless and irrelevant content. In this paper we have worked on the Quora insincere questions (questions which are based on false assumptions or questions which are trying to make a statement rather than seeking for helpful answers) dataset in order to identify user insincere questions, so that Quora can eliminate those questions from their platform and ultimately improve the communication among users over the platform. Previously, a research was carried out with recurrent neural network and pretrained glove word embeddings, that achieved the F1 score of 0.69. The proposed study has used a pre-trained ULMFiT model. This model has outperformed the previous model with an F1 score of 0.91, which is much higher than the previous studies.

---

Keywords

---