Hate Speech Detection Using Transformer Ensembles on the HASOC Dataset

Alonso, Pedro; Saini, Rajkumar; Kovács, George L.

doi:10.1007/978-3-030-60276-5_2

Cited by 24 publications

(18 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lastly, it is important to note here, that while in these experiments results attained with RoBERTa were not improved by the use of additional labeled training data, one can find opposing results in the literature. After the initial submission of this paper, Alonso et al [3] used 1 million tweets from the OffensEval training set to fine-tune the same RoBERTa model, then fine-tuned the resulting model further using the same five folds that we applied in our experiments, and Fig. 2 Hateful or offensive tweets where the hateful/offensive part is in Hindi found that the resulting ensemble performed better than the ensemble without fine-tuning.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Challenges of Hate Speech Detection in Social Media

2021

Self Cite

View full text Add to dashboard Cite

The detection of hate speech in social media is a crucial task. The uncontrolled spread of hate has the potential to gravely damage our society, and severely harm marginalized people or groups. A major arena for spreading hate speech online is social media. This significantly contributes to the difficulty of automatic detection, as social media posts include paralinguistic signals (e.g. emoticons, and hashtags), and their linguistic content contains plenty of poorly written text. Another difficulty is presented by the context-dependent nature of the task, and the lack of consensus on what constitutes as hate speech, which makes the task difficult even for humans. This makes the task of creating large labeled corpora difficult, and resource consuming. The problem posed by ungrammatical text has been largely mitigated by the recent emergence of deep neural network (DNN) architectures that have the capacity to efficiently learn various features. For this reason, we proposed a deep natural language processing (NLP) model—combining convolutional and recurrent layers—for the automatic detection of hate speech in social media data. We have applied our model on the HASOC2019 corpus, and attained a macro F1 score of 0.63 in hate speech detection on the test set of HASOC. The capacity of DNNs for efficient learning, however, also means an increased risk of overfitting. Particularly, with limited training data available (as was the case for HASOC). For this reason, we investigated different methods for expanding resources used. We have explored various opportunities, such as leveraging unlabeled data, similarly labeled corpora, as well as the use of novel models. Our results showed that by doing so, it was possible to significantly increase the classification score attained.

show abstract

Section: Discussionmentioning

confidence: 99%

“…https ://paper swith code.com/task/text-class ifica tion 3. https ://paper swith code.com/task/senti ment-analy sis 4.…”

mentioning

confidence: 99%

Challenges of Hate Speech Detection in Social Media

2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Most of these approaches outperform traditional machine learning models. In addition, the recent advancements in language representation models such as ELMO [41], BERT [7], and XLM-R [9] have led to the considerable use of transformer-based pre-trained language models in hate speech and offensive language detection with competitive and promising results [42][43][44].…”

Section: A Hate Speech and Offensive Language Detectionmentioning

confidence: 99%

Cross-Lingual Few-Shot Hate Speech and Offensive Language Detection Using Meta Learning

2022

View full text Add to dashboard Cite

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.

show abstract

“…Fortuna and Nunes (2018) conducted a systematic review on automatic detection of hate speech in text and enumerated dictionary-based, rule-based, and feature-based techniques, as well as early deep learning models applied to this task. Since then, deep learning models, such as convolutional neural networks (CNN) (Gambäck & Sikdar, 2017), recurrent neural networks (RNN) (Zhang et al, 2018b), and transformers (Alonso et al, 2020), have been applied to build automatic abuse detection systems, and high performances have been achieved as these algorithms improved. Naseem et al (2020) showed that besides the training algorithms, preprocessing methods significantly impact the performance of the trained classifiers, which is often overlooked.…”

Section: Algorithmsmentioning

confidence: 99%

Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspective

Kiritchenko

Nejadgholi

Fraser

2021

jair

View full text Add to dashboard Cite

The pervasiveness of abusive content on the internet can lead to severe psychological and physical harm. Significant effort in Natural Language Processing (NLP) research has been devoted to addressing this problem through abusive content detection and related sub-areas, such as the detection of hate speech, toxicity, cyberbullying, etc. Although current technologies achieve high classification performance in research studies, it has been observed that the real-life application of this technology can cause unintended harms, such as the silencing of under-represented groups. We review a large body of NLP research on automatic abuse detection with a new focus on ethical challenges, organized around eight established ethical principles: privacy, accountability, safety and security, transparency and explainability, fairness and non-discrimination, human control of technology, professional responsibility, and promotion of human values. In many cases, these principles relate not only to situational ethical codes, which may be context-dependent, but are in fact connected to universal human rights, such as the right to privacy, freedom from discrimination, and freedom of expression. We highlight the need to examine the broad social impacts of this technology, and to bring ethical and human rights considerations to every stage of the application life-cycle, from task formulation and dataset design, to model training and evaluation, to application deployment. Guided by these principles, we identify several opportunities for rights-respecting, socio-technical solutions to detect and confront online abuse, including ‘nudging’, ‘quarantining’, value sensitive design, counter-narratives, style transfer, and AI-driven public education applications.evaluation, to application deployment. Guided by these principles, we identify several opportunities for rights-respecting, socio-technical solutions to detect and confront online abuse, including 'nudging', 'quarantining', value sensitive design, counter-narratives, style transfer, and AI-driven public education applications.

show abstract

Hate Speech Detection Using Transformer Ensembles on the HASOC Dataset

Cited by 24 publications

References 36 publications

Challenges of Hate Speech Detection in Social Media

Challenges of Hate Speech Detection in Social Media

Cross-Lingual Few-Shot Hate Speech and Offensive Language Detection Using Meta Learning

Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspective

Contact Info

Product

Resources

About