Context-Aware Deep Learning Model for Detection of Roman Urdu Hate Speech on Social Media Platform

Abstract

Over the last two decades, social media platforms have grown dramatically. Twitter and Facebook are the two most popular social media platforms, with millions of active users posting billions of messages daily. These platforms allow users to have freedom of expression. However, some users exploit this facility by disseminating hate speeches. Manual detection and censorship of such hate speeches are impractical; thus, an automatic detection mechanism is required to detect and counter hate speeches in a real-time environment. Most research in hate speech detection has been carried out in the English language. Still, minimal work has been explored in other languages, mainly Urdu written in Roman Urdu script. A few research have attempted machine learning, and deep learning models for Roman Urdu hate speech detection; however, due to a scarcity of Roman Urdu resources, and a large corpus with defined annotation rules, a robust hate speech detection model is still required. With this motivation, this study contributes in the following manner: we developed annotation guidelines for Roman Urdu Hate Speech. Second, we constructed a new Roman Urdu Hate Speech Dataset (RU-HSD-30K) that was annotated by a team of experts using the annotation rules. To the best of our knowledge, the Bi-LSTM model with an attention layer for Roman-Urdu Hate Speech Detection has not been explored. Therefore, we developed a contextaware Roman Urdu Hate Speech detection model based on Bi-LSTM with an attention layer and used custom word2vec for word embeddings. Finally, we examined the effect of lexical normalization of Roman Urdu words on the performance of the proposed model. Different traditional as well as deep learning models, including LSTM and CNN models, were used as baseline models. The performance of the models was assessed in terms of evaluation matrices like accuracy, precision, recall, and F1-score. The generalization of each model is also evaluated on a cross-domain dataset. Experimental results revealed that Bi-LSTM with attention outperformed the traditional machine learning models and other deep learning models with an accuracy score of 0.875 and an F-Score of 0.885. In addition, the results demonstrated that our suggested model (Bi-LSTM with Attention Layer) is more general than previous models when applied to unseen data. The results confirmed that lexical normalization of Roman Urdu words enhanced the performance of the suggested model.

Hate speech detection in social media: Techniques, recent trends, and future challenges

“…Among the diverse topics investigated, the predominant data reservoir for numerous studies has been derived from Twitter. Subsequently, Facebook has been another substantial source (Bilal et al, 2022; MacAvaney et al, 2019; Mozafari et al, 2022; Rodriguez et al, 2022; Sreelakshmi et al, 2020). Additionally, alternative platforms such as YouTube comments have been utilized (Kumar Roy et al, 2022; Roy et al, 2022; Sajid et al, 2020), along with resources like Wikipedia (Beddiar et al, 2021) and diverse online platforms (Alatawi et al, 2021; Beddiar et al, 2021).…”

“…Traditional machine learning SVM (Ali et al, 2021;Balouchzahi et al, 2021;Oriola & Kotze, 2020;Saeed Tawfik, 2020;Sajid et al, 2020;Sharma & Shrivastava, 2018;Vogel & Meghana, 2021;Watanabe et al, 2018) NB (Priyadarshini et al, 2023;Saeed Tawfik, 2020;Sajid et al, 2020;Sharma & Shrivastava, 2018) RF (MacAvaney et al, 2019;Oriola & Kotze, 2020;Saeed Tawfik, 2020;Sharma & Shrivastava, 2018) LR (Balouchzahi et al, 2021;Oriola & Kotze, 2020;Saeed Tawfik, 2020;Sajid et al, 2020) GB (Oriola & Kotze, 2020;Sajid et al, 2020) DT (Priyadarshini et al, 2023) NLP (Das et al, 2021;Saeed Tawfik, 2020;Sharma & Shrivastava, 2018;Vogel & Meghana, 2021;Watanabe et al, 2018) K-means (Ali et al, 2021) Word2vec (Balouchzahi et al, 2021;Priyadarshini et al, 2023) GloVe (Priyadarshini et al, 2023;Rodriguez et al, 2022) Deep learning CNN (Bilal et al, 2022;Das et al, 2021;Ghosh et al, 2023;Zhang & Luo, 2018;Zhou et al, 2020) LSTM (Bilal et al, 2022) BERT (Alzahrani & Jololian, 2021;…”

Hybrid Convolutional Recurrent Neural Network for Cyberbullying Detection on Textual Data

“…1, our advanced schema elucidates two divergent pathways for textual data analytics. The inaugural pathway is rooted in initial data cleansing, segueing into attribute derivation using NLP methodologies [26][27][28][29]. These mechanisms transform textual elements, priming them for subsequent analysis by conventional computational algorithms, which establish the foundational methods.…”

Abusive Language Detection in Urdu Text: Leveraging Deep Learning and Attention Mechanism

“…Research conducted by [20] introduced a new dataset, RU-HSD-30K, designed specifically for identifying hate speech in Roman Urdu on social media. The dataset underwent validation by experts.…”