The use of offensive language in user-generated content is a serious problem that needs to be addressed with the latest technology. The field of Natural Language Processing (NLP) can support the ...automatic detection of offensive language. In this survey, we review previous NLP studies that cover Arabic offensive language detection. This survey investigates the state-of-the-art in offensive language detection for the Arabic language, providing a structured overview of previous approaches, including core techniques, tools, resources, methods, and main features used. This work also discusses the limitations and gaps of the previous studies. Findings from this survey emphasize the importance of investing further effort in detecting Arabic offensive language, including the development of benchmark resources and the invention of novel preprocessing and feature extraction techniques.
Abstract In the article, we describe recent trends in the detection of hate speech and offensive language on social media. We accord from the latest studies and scientific contributions. The article ...describes current trends and the most used methods in connection with the detection of hate speech and offensive language. At the same time, we focus on the importance of emoticons, hashtags, and swearing in the field of social networks. We point out the topicality of the selected topic, describe the next direction of our work, and suggest possible solutions to current problems in this field of research.
In the era of the explosion of digital content of large‐scale self‐media, user‐friendly social platforms such as Twitter and Facebook, provide opportunities for people to express their ideas and ...opinions freely. Due to lack of restrictions, hateful speech and its exposure can have profound psychological impacts on society. Current social networking platform is over‐reliant on the manual check, and it is labor‐intensive and time‐consuming. Although there are many machines learning methods for the detection of hate speech, short text with character limit on social platforms is more challenging for the detection of hate speech and offensive language. To address the problem of data sparsity, we have proposed a topic memory model for hate speech and offensive language detection (abbreviated as TM‐HOL). Potential topics are generated with our encoder and decoder to enrich short text features. Two memory matrices correspond to the topic words and the text, and the hate feature matrix is used to learn the syntactic features. It is demonstrated that our proposed method is effective on three datasets, performing better weighted‐F1.
The detection of toxic language in the Arabic language has emerged as an active area of research in recent years, and reviewing the existing datasets employed for training the developed solutions has ...become a pressing need. This paper offers a comprehensive survey of Arabic datasets focused on online toxic language. We systematically gathered a total of 54 available datasets and their corresponding papers and conducted a thorough analysis, considering 18 criteria across four primary dimensions: availability details, content, annotation process, and reusability. This analysis enabled us to identify existing gaps and make recommendations for future research works. For the convenience of the research community, the list of the analysed datasets is maintained in a GitHub repository.
In recent years, unethical behavior in the cyber-environment has been revealed. The presence of offensive language on social media platforms and automatic detection of such language is becoming a ...major challenge in modern society. The complexity of natural language constructs makes this task even more challenging. Until now, most of the research has focused on resource-rich languages like English. Roman Urdu and Urdu are two scripts of writing the Urdu language on social media. The Roman script uses the English language characters while the Urdu script uses Urdu language characters. Urdu and Hindi languages are similar with the only difference in their writing script but the Roman scripts of both languages are similar. This study is about the detection of offensive language from the user's comments presented in a resource-poor language Urdu. We propose the first offensive dataset of Urdu containing user-generated comments from social media. We use individual and combined n-grams techniques to extract features at character-level and word-level. We apply seventeen classifiers from seven machine learning techniques to detect offensive language from both Urdu and Roman Urdu text comments. Experiments show that the regression-based models using character n-grams show superior performance to process the Urdu language. Character-level tri-gram outperforms the other word and character n-grams. LogitBoost and SimpleLogistic outperform the other models and achieve 99.2% and 95.9% values of F-measure on Roman Urdu and Urdu datasets respectively. Our designed dataset is publically available on GitHub for future research.
Since cyberbullying impacts both individual victims and entire society, research on abusive language and its detection has attracted attention in recent years. Because social media sites like ...Facebook, Instagram, Twitter, and others are so widely accessible, hate speech, bullying, sexism, racism, aggressive material, harassment, poisonous comments, and other types of abuse have all substantially increased. Due to the critical requirement to detect, regulate, and limit the spread of harmful content on social networking sites, we conducted this study to automate the detection of offensive language or cyberbullying. We created a new Arabic balanced data set to be used in the offensive detection process because having a balanced data set for a model would result in improved accuracy models. Recently, the performance of single classifiers has been improved using ensemble machine learning. The purpose of this study is to examine the effectiveness of several single and ensemble machine learning algorithms in identifying Arabic text that contains foul language and cyberbullying. Applying them to three Arabic datasets, we have selected three machine learning classifiers and three ensemble models for this aim. Two of them are offensive datasets that are readily accessible in the public, while the third one was created. The results showed that the single learner machine learning strategy is inferior to the ensemble machine learning methodology. Voting performs is the best performing trained ensemble machine learning classifier, outperforming the best single learner classifier (65.1%, 76.2%, and 98%) for the same datasets with accuracy scores of (71.1%, 76.7%, and 98.5%) for each of the three datasets used. Finally, we improve the voting technique’s performance through hyperparameter tuning on the Arabic cyberbullying data set.
Sentiment analysis is an NLP task that gained the interest of many researchers in various languages and recently in the Arabic language. We have encountered several challenges when dealing with this ...task, including sarcasm detection. In this article, we aim to exploit sarcastic characteristics to improve the accuracy of the sentiment analysis system. Sarcasm is difficult to detect because it is implicit and characterized by the presence of positive words in a negative context. We have then extracted a variety of features to define context incongruity and the opposition between the objective and subjective sentences. Offensive language and hate speech correspond to expressions that hurt others. The detection of offensive language is based on identifying offensive terms that are strongly negative and helpful to detect negative expressions. Thus, we have manually and automatically constructed sentimental, offensive and sarcastic lexicons and collected others. In the same way, many corpora either ironic (sarcastic, offensive) or sentimental (positive, negative) were collected. As sarcasm is a major challenge for the sentiment analysis system, we have built a balanced system that contains positive and negative (sarcastic, offensive) tweets. Since the analyzed corpus is multidialectal, we have used a cross dialect lexicon that retains meaning when passing from one dialect to another. Besides the Arabic dialect common characteristics, the classification was enhanced by the detection of the specificities of some dialects that use negation clitics as well as negation words to negate a term. The experiments prove that the enhancement of a sentiment analysis system by sarcastic features improved the results by 8% to reach 84.17% of accuracy using a classical machine learning approach and 80.36% using a Deep learning approach. The classical machine learning approach is improved afterward based on the expansion of the BOW lexicon and the reduction of the characteristic vector to reach an accuracy of 89.24%. This method is multilingual because the built model can be language independent. Indeed, it is enough to have the corresponding resources to apply the system to other languages.
Offensive content is pervasive in social media and a reason for concern to companies and government organizations. Several studies have been recently published investigating methods to detect the ...various forms of such content (e.g., hate speech, cyberbullying, and cyberaggression). The clear majority of these studies deal with English partially because most annotated datasets available contain English data. In this article, we take advantage of available English datasets by applying cross-lingual contextual word embeddings and transfer learning to make predictions in low-resource languages. We project predictions on comparable data in Arabic, Bengali, Danish, Greek, Hindi, Spanish, and Turkish. We report results of 0.8415 F1 macro for Bengali in TRAC-2 shared task 23, 0.8532 F1 macro for Danish and 0.8701 F1 macro for Greek in OffensEval 2020 58, 0.8568 F1 macro for Hindi in HASOC 2019 shared task 27, and 0.7513 F1 macro for Spanish in in SemEval-2019 Task 5 (HatEval) 7, showing that our approach compares favorably to the best systems submitted to recent shared tasks on these three languages. Additionally, we report competitive performance on Arabic and Turkish using the training and development sets of OffensEval 2020 shared task. The results for all languages confirm the robustness of cross-lingual contextual embeddings and transfer learning for this task.
Automatic detection of abusive online content such as hate speech, offensive language, threats, etc. has become prevalent in social media, with multiple efforts dedicated to detecting this phenomenon ...in English. However, detecting hatred and abuse in low-resource languages is a non-trivial challenge. The lack of sufficient labeled data in low-resource languages and inconsistent generalization ability of transformer-based multilingual pre-trained language models for typologically diverse languages make these models inefficient in some cases. We propose a meta learning-based approach to study the problem of few-shot hate speech and offensive language detection in low-resource languages that will allow hateful or offensive content to be predicted by only observing a few labeled data items in a specific target language. We investigate the feasibility of applying a meta learning approach in cross-lingual few-shot hate speech detection by leveraging two meta learning models based on optimization-based and metric-based (MAML and Proto-MAML) methods. To the best of our knowledge, this is the first effort of this kind. To evaluate the performance of our approach, we consider hate speech and offensive language detection as two separate tasks and make two diverse collections of different publicly available datasets comprising 15 datasets across 8 languages for hate speech and 6 datasets across 6 languages for offensive language. Our experiments show that meta learning-based models outperform transfer learning-based models in a majority of cases, and that Proto-MAML is the best performing model, as it can quickly generalize and adapt to new languages with only a few labeled data points (generally, 16 samples per class yields an effective performance) to identify hateful or offensive content.
Abstract
Slurs are pejorative terms for groups of people, relating to for example their nationality, their sexual
orientation, etc. While there is a lot of discussion about slurs, they are typically ...characterized in relation to a neutral noun.
In this article we will explore this distinction between neutral and offensive group labels. By means of a small experiment, we
show that slurs are indeed considered to be more hurtful than their corresponding ‘neutral’ nouns, but that at least some of these
nouns themselves are experienced as more hurtful than adjective noun combinations. We suggest that the results are in line with
analyses in which the degree to which a term is considered to be hurtful is based on its inherent (i.e. conventionalized)
properties, as well as the context in which it is used. We suggest that such analyses could be extended to nouns, such that terms
can be neutral or non-neutral to various degrees.