Implementation of Machine Learning to Detect Hate Speech in Bangla Language

Ahammed, Shovon; Rahman, Mostafizur; Niloy, Mahedi Hasan; Chowdhury, S. M. Mazharul Hoque

doi:10.1109/smart46866.2019.9117214

Cited by 26 publications

(9 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This research experiments on eight ML models such as SVM, MNB, random forest (RF), logistic regression (LR), long short term memory (LSTM), bidirectional LSTM (BiLSTM), CNN-BiLSTM, and BERT, which give better outputs in several studies for classifying a text for the Bengali language. In the case of classical ML models, the SVM model outperformed in [3], [7], [8], [11], whereas, the MNB model showed better results in [4], [15]. However, the RF and the LR presented the higher accuracy in [16] and [17], respectively.…”

Section: Model Classifiersmentioning

confidence: 90%

Detecting cyberbullying text using the approaches with machine learning models for the low-resource Bengali language

Hoque,

Seddiqui

2024

IJ-AI

View full text Add to dashboard Cite

The rising usage of social media sites and the advances in communication technologies have led to a considerable increase in cyberbullying events. Here, people are intimidated, harassed, and humiliated via digital messaging. To identify cyberbullying texts, several research have been undertaken in English and other languages with abundant resources, but relatively few studies have been conducted in low-resource languages like Bengali. This research focuses on Bengali text to ﬁnd cyberbullying material by experimenting with pre-processing, feature selection, and three types of machine learning (ML) models: classical ML, deep learning (DL), and transformer learning. In classical ML, four models, support vector machine (SVM), multinomial Naive Bayes (MNB), random forest (RF), and logistic regression (LR) are used. In DL, three models, long short term memory (LSTM), Bidirectional LSTM, and convolutional neural network with bidirectional LSTM (CNN-BiLSTM) are employed. As the transformer-based pretrained model, bidirectional encoder representations from transformers (BERT) is utilized. Using our proposed pre-processing tasks, the MNB-based approach achieves the best accuracy of 78.816% among the other classical ML models, the LSTM-based approach gains the highest result of 77.804% accuracy among the DL models, and the BERT-based approach outperforms both with 80.165% accuracy.

show abstract

Section: Model Classifiersmentioning

confidence: 90%

Detecting cyberbullying text using the approaches with machine learning models for the low-resource Bengali language

Hoque,

Seddiqui

2024

IJ-AI

View full text Add to dashboard Cite

show abstract

“…Chakraborty and Seddiqui [19] used machine and deep learning to classify Bangla texts, with SVM performing best with 78% accuracy. Similarly, a maximum of 72% accuracy was achieved by Ahammed et al [20]. They gathered their Bengali data from Facebook.…”

Section: Related Workmentioning

confidence: 90%

Natural language processing and machine learning based cyberbullying detection for Bangla and Romanized Bangla texts

et al. 2021

View full text Add to dashboard Cite

“…In the study 15 , researchers worked intending to identify hate speech in the Bengali language. Their study contributes to the creation of the up-to-date dataset for hatred speech identification using the Bangla language and the application of the models for detection.…”

Section: Related Workmentioning

confidence: 99%

Detection of Abusive Bengali Comments for Mixed Social Media Data Using Machine Learning

Sultana

Redoy

Nahian

et al. 2023

Preprint

View full text Add to dashboard Cite

Most people around the world use social media in their daily lives as a result we can see that it has become an integral part of our lives. Moreover, many people use social media for their livelihood. Social media has a lot of influence on our life from different aspects. Although there are many positive aspects, the trend of negative comments on social media has become a serious problem these days. Through this study, we have detected bad comments made in the Bengali language on social media using machine learning algorithms and measured those performances. Although much work has been done on this issue in other languages, it is scarce in the Bengali language. We have used six different types of machine learning algorithms for this study and the algorithms used are Logistic Regression (LR), Multinomial Naive Bayes (MNB), Random Forest (RF), Support vector machine (SVM), K-Nearest Neighbor (KNN), Gradient Boosting (GB). Among all the algorithms used in this study, SVM gave the best results with an accuracy of 85.7%.

show abstract

Implementation of Machine Learning to Detect Hate Speech in Bangla Language

Cited by 26 publications

References 4 publications

Detecting cyberbullying text using the approaches with machine learning models for the low-resource Bengali language

Detecting cyberbullying text using the approaches with machine learning models for the low-resource Bengali language

Natural language processing and machine learning based cyberbullying detection for Bangla and Romanized Bangla texts

Detection of Abusive Bengali Comments for Mixed Social Media Data Using Machine Learning

Contact Info

Product

Resources

About