Search

During the COVID-19 pandemic, online social media platforms such as Twitter facilitate the exchange of information among people. However, the prevalence of "infodemic" such as online hate speech has exacerbated social rifts, discrimination, prejudice and even hate crimes. Timely and effective detection of the hate speech will help create a healthy public opinion environment. Most of the current COVID-19-related hate speech research focuses on a single language, such as English. In this paper, we introduce a cross-lingual transfer learning method, aiming to contribute to hate speech detection in low-resource languages. We propose a deep learning based model to classify hate speech with a pre-trained language model for multilingual text embedding. Data augmentation and cross-lingual contrastive learning are then utilized to further improve the performance of cross-lingual knowledge transfer. To evaluate our method, we collected three publicly available annotated COVID-19-related hate speech datasets on Twitter, i.e., two in English and one in German. Furthermore, a Chinese dataset based on Weibo is constructed to expand multilingual data. The experimental results across three languages illustrate the effectiveness of our method for cross-lingual hate speech detection. Test F1-scores of our method for English, Chinese, German as transfer target languages can reach up to 0.728, 0.799 and 0.612 respectively, which are on average better than other baselines. • Suggested a cross-lingual COVID-19-related hate speech detection problem. • Introduced cross-lingual contrastive learning. • Validated model performance on datasets in three languages. [ABSTRACT FROM AUTHOR]

Nowadays, due to the great uncontrolled content posted daily on the Web, there has also been a huge increase in the dissemination of hate speech worldwide. Social media, blogs and community forums are examples where people are freely allowed to communicate. However, freedom of expression is not always respectful since offensive or insulting language is sometimes used. Social media companies often rely on users and content moderators to report on this type of content. Nevertheless, due to the large amount of content generated every day on the Web, automatic systems based on Natural Language Processing techniques are required for identifying abusive language online. To date, most of the systems developed to combat this problem are mainly focused on English content, but this issue is a worldwide concern and therefore other languages such as Spanish are involved. In this paper, we address the task of Spanish hate speech identification on social media and provide a deeper understanding of the capabilities of new techniques based on machine learning. In particular, we compare the performance of Deep Learning methods with recently pre-trained language models based on Transfer Learning as well as with traditional machine learning models. Our main contribution is the achievement of promising results in Spanish by applying multilingual and monolingual pre-trained language models such as BERT, XLM and BETO. • Addressing hate speech detection on social media for Spanish. • Comparing the performance of Deep Learning and Machine Learning models. • Evaluating recent pre-trained language models based on Transformer mechanism. • Comparing pre-trained multilingual and monolingual models available for Spanish. • Conducting an error analysis in order to understand the difficulty of the task. [ABSTRACT FROM AUTHOR]

• Developed browser plugins to visualize hate speech live on Facebook & Twitter. • Designed proof of concepts for personalized dashboards for Twitter & Instagram. • Optimized classifiers for Hate Speech with tests on standard datasets. • Application areas for the tool are discussed. The multi-fold growth of the social media user-base fuelled a substantial increase in the amount of hate speech posts on social media platforms. The enormous data volume makes it hard to capture such cases and either moderate or delete them. This paper presents an approach to detect and visualize online aggression, a special case of hate speech, over social media. Aggression is categorized into overtly aggressive (OAG), covertly aggressive (CAG), and non-aggressive labels (NAG). We have designed a user interface based on a web browser plugin over Facebook and Twitter to visualize the aggressive comments posted on the Social media user's timelines. This plugin interface might help to the security agency to keep a tab on the social media stream. It also provides citizens with a tool that is typically only available for large enterprises. The availability of such a tool alleviates the technological imbalance between industry and citizens. Besides, the system might be helpful to the research community to create further tools and prepare weakly labeled training data in a few minutes using comments posted by users on celebrity's Facebook, Twitter timeline. We have reported the results on a newly created dataset of user comments posted on Facebook and Twitter using our proposed plugins and the standard Trolling Aggression Cyberbullying 2018 (TRAC) dataset in English and code-mixed Hindi. Various classifiers like Support Vector Machine (SVM), Logistic regression, deep learning model based on Convolution Neural Network (CNN), Attention-based model, and the recently proposed BERT pre-trained language model by Google AI, have been used for aggression classification. The weighted F1-score of around 0.64 and 0.62 is achieved on TRAC Facebook English and Hindi datasets while on Twitter English and Hindi datasets, the weighted F1-score is 0.58 and 0.50, respectively. [ABSTRACT FROM AUTHOR]