Machine Learning Approach to Detection of Offensive Language in Online Communication in Arabic

Alakrot, Azalden; Fraifer, Muftah; Nikolov, Nikola S.

doi:10.1109/mi-sta52233.2021.9464402

Cited by 8 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results proved that the Precision and the Recall of the BERT-based models are almost alike. This means that these models are not as biased as the baseline models, such as LSTM [43] and LinearSVC [44], and perform equally well for both the positive and the negative comments.…”

Section: Resultsmentioning

confidence: 95%

“…Taking a deeper look at why BERT-based models outperformed other language models such as LSTM [43] and LinearSVC [44], in the past, conventional language models could only interpret text input sequentially -either from right to left or from left to right -but not simultaneously. BERT is unique since it can simultaneously read in both directions.…”

Section: Resultsmentioning

confidence: 99%

“…We will also take the Linear Support Vector Classification (LinearSVC) based on the approach presented by Alakrot et al [44], in which they demonstrated that LinearSVC can reach a 90% accuracy, which is higher than our LSTM-based approach, reaching an accuracy of 82%.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Detecting Hateful and Offensive Speech in Arabic Social Media Using Transfer Learning

Boulouard

Ouaissa

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

The democratization of access to internet and social media has given an opportunity for every individual to openly express his or her ideas and feelings. Unfortunately, this has also created room for extremist, racist, misogynist, and offensive opinions expressed either as articles, posts, or comments. While controlling offensive speech in English-, Spanish-, and French- speaking social media communities and websites has reached a mature level, it is much less the case for their counterparts in Arabic-speaking countries. This paper presents a transfer learning solution to detect hateful and offensive speech on Arabic websites and social media platforms. This paper will compare the performance of different BERT-based models trained to classify comments as either abusive or neutral. The training dataset contains comments in standard Arabic as well as four dialects. We will also use their English translations for comparative purposes. The models were evaluated based on five metrics: Accuracy, Precision, Recall, F1-Score, and Confusion Matrix.

show abstract

Section: Resultsmentioning

confidence: 95%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Detecting Hateful and Offensive Speech in Arabic Social Media Using Transfer Learning

Boulouard

Ouaissa

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The work of [41] examined several ML classifiers using various feature extraction and selection techniques on a dataset of YouTube comments in Arabic to detect offensive language in online communications. They applied a vari-ety of feature transformation techniques applied, including logistic regression with L1 regularisation (LR-L1), feature ranking with recursive feature elimination (RFE), Extra-TreesClassifier, tree-based ensemble methods, and singularvalue decomposition (SVD).…”

Section: Related Workmentioning

confidence: 99%

Offensive Language Detection in Arabic Social Networks Using Evolutionary-Based Classifiers Learned From Fine-Tuned Embeddings

et al. 2022

View full text Add to dashboard Cite

Social networks facilitate communication between people from all over the world. Unfortunately, the excessive use of social networks leads to the rise of antisocial behaviors such as the spread of online offensive language, cyberbullying (CB), and hate speech (HS). Therefore, abusive\offensive and hate detection become a crucial part of cyberharassment. Manual detection of cyberharassment is cumbersome, slow, and not even feasible in rapidly growing data. In this study, we addressed the challenges of automatic detection of the offensive tweets in the Arabic language. The main contribution of this study is to design and implement an intelligent prediction system encompassing a two-stage optimization approach to identify and classify the offensive from the non-offensive text. In the first stage, the proposed approach fine-tuned the pre-trained word embedding models by training them for several epochs on the training dataset. The embeddings of the vocabularies in the new dataset are trained and added to the old embeddings. While in the second stage, it employed a hybrid approach of two classifiers, namely XGBoost and SVM, and a genetic algorithm (GA) to mitigate the drawback of the classifiers in finding the optimal hyperparameter values to run the proposed approach. We tested the proposed approach on Arabic Cyberbullying Corpus (ArCybC), which contains tweets collected from four Twitter domains: gaming, sports, news, and celebrities. The ArCybC dataset has four categories: sexual, racial, intelligence, and appearance. The proposed approach produced superior results, in which the SVM algorithm with the Aravec SkipGram word embedding model achieved an accuracy rate of 88.2% and an F1-score rate of 87.8%.

show abstract

“…One of the results of the development of science is the benime application, this benime application is very interesting to be used as a learning medium in the online learning system at this time. There are still many educators in elementary schools who have not involved computers in the teaching and learning process, so that students still do not understand the use of computers and the use of the benime application (Alakrot, 2021).…”

Section: Introductionmentioning

confidence: 99%

Use of Benime Application in Arabic Language Learning

Hael,

Hafiz,

Deng

2023

Lingeduca: J. of Language and Education Studies

View full text Add to dashboard Cite

Language is a very basic thing for every human being, not only for communication but also as a forum for the prosecution of knowledge. At this time, other languages are urgently needed because of the increasing circulation of information using other languages, as well as Arabic itself. In the process of learning Arabic, there are several problems or difficulties faced at the IT Ar-Rahman Palangki Elementary School. With the development of technology at this time, therefore technology can be a solution to the difficulties brought into the teaching and learning process of Arabic at SD IT Ar-Rahman Palangki. This is due to the technology that we can use to assist in making interesting learning media, especially applications that can be accessed on Android in the form of images, sounds, and moving animations, such as the Benime application. The benime app itself is an animated video maker app for a more interesting percentage.

show abstract

Machine Learning Approach to Detection of Offensive Language in Online Communication in Arabic

Cited by 8 publications

References 15 publications

Detecting Hateful and Offensive Speech in Arabic Social Media Using Transfer Learning

Detecting Hateful and Offensive Speech in Arabic Social Media Using Transfer Learning

Offensive Language Detection in Arabic Social Networks Using Evolutionary-Based Classifiers Learned From Fine-Tuned Embeddings

Use of Benime Application in Arabic Language Learning

Contact Info

Product

Resources

About