Detection of offensive terms in resource-poor language using machine learning algorithms

Muhammad Owais Raza; Naeem Ahmed Mahoto; Mohammed Hamdi; Mana Saleh Al Reshan; Adel Rajab; Asadullah Shaikh

doi:10.7717/peerj-cs.1524

Detection of offensive terms in resource-poor language using machine learning algorithms

PeerJ Comput Sci. 2023 Aug 29:9:e1524. doi: 10.7717/peerj-cs.1524. eCollection 2023.

Authors

Muhammad Owais Raza¹, Naeem Ahmed Mahoto¹, Mohammed Hamdi², Mana Saleh Al Reshan³, Adel Rajab², Asadullah Shaikh³

Affiliations

¹ Department of Software Engineering, Mehran University of Engineering and Technology Jamshoro, Jamshoro, Pakistan.
² Department of Computer Science, Najran University, Najran, Najran, Saudi Arabia.
³ Department of Information Systems, Najran University, Najran, Najran, Saudi Arabia.

Abstract

The use of offensive terms in user-generated content on different social media platforms is one of the major concerns for these platforms. The offensive terms have a negative impact on individuals, which may lead towards the degradation of societal and civilized manners. The immense amount of content generated at a higher speed makes it humanly impossible to categorise and detect offensive terms. Besides, it is an open challenge for natural language processing (NLP) to detect such terminologies automatically. Substantial efforts are made for high-resource languages such as English. However, it becomes more challenging when dealing with resource-poor languages such as Urdu. Because of the lack of standard datasets and pre-processing tools for automatic offensive terms detection. This paper introduces a combinatorial pre-processing approach in developing a classification model for cross-platform (Twitter and YouTube) use. The approach uses datasets from two different platforms (Twitter and YouTube) the training and testing the model, which is trained to apply decision tree, random forest and naive Bayes algorithms. The proposed combinatorial pre-processing approach is applied to check how machine learning models behave with different combinations of standard pre-processing techniques for low-resource language in the cross-platform setting. The experimental results represent the effectiveness of the machine learning model over different subsets of traditional pre-processing approaches in building a classification model for automatic offensive terms detection for a low resource language, i.e., Urdu, in the cross-platform scenario. In the experiments, when dataset D1 is used for training and D2 is applied for testing, the pre-processing approach named Stopword removal produced better results with an accuracy of 83.27%. Whilst, in this case, when dataset D2 is used for training and D1 is applied for testing, stopword removal and punctuation removal were observed as a better preprocessing approach with an accuracy of 74.54%. The combinatorial approach proposed in this paper outperformed the benchmark for the considered datasets using classical as well as ensemble machine learning with an accuracy of 82.9% and 97.2% for dataset D1 and D2, respectively.

Keywords: Classification model; Machine learning; Offensive terms; Resource-poor language.

Grants and funding

The authors received funding from the Deanship of Scientific Research at Najran University for this research through a grant (NU/RG/SERC/12/33) under the Research Groups Funding program at Najran University, Kingdom of Saudi Arabia. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.