SWE2: SubWord Enriched and Significant Word Emphasized Framework for Hate Speech Detection

Mou, Guanyi; Ye, Pengyi; Lee, Kyumin

doi:10.1145/3340531.3411990

Cited by 11 publications

(5 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…User-based features, including content history, meta-attributes, and user profile can be used to detect hate signals (Waseem, 2016;Chatzakou et al, 2017;Unsvåg and Gambäck, 2018). To capture word semantics better than bag-of-words; word embeddings, such as GloVe (Pennington et al, 2014), are utilized to detect abusive and hatred language (Nobata et al, 2016;Mou et al, 2020). Character and phonetic-level embeddings are also studied for hate speech to resolve the issues related to noisy text of social media (Mou et al, 2020).…”

Section: Methods For Hate Speech Detectionmentioning

confidence: 99%

“…To capture word semantics better than bag-of-words; word embeddings, such as GloVe (Pennington et al, 2014), are utilized to detect abusive and hatred language (Nobata et al, 2016;Mou et al, 2020). Character and phonetic-level embeddings are also studied for hate speech to resolve the issues related to noisy text of social media (Mou et al, 2020). Instead of extracting hand-crafted features; deep neural networks, such as CNN (Kim, 2014) and LSTM (Hochreiter and Schmidhuber, 1997), are applied to extract deep features to represent text semantics.…”

Section: Methods For Hate Speech Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Large-Scale Hate Speech Detection with Cross-Domain Transfer

Toraman¹,

Şahi̇nuç²,

Yılmaz³

2022

Preprint

View full text Add to dashboard Cite

The performance of hate speech detection models relies on the datasets on which the models are trained. Existing datasets are mostly prepared with a limited number of instances or hate domains that define hate topics. This hinders large-scale analysis and transfer learning with respect to hate domains. In this study, we construct large-scale tweet datasets for hate speech detection in English and a low-resource language, Turkish, consisting of human-labeled 100k tweets per each. Our datasets are designed to have equal number of tweets distributed over five domains. The experimental results supported by statistical tests show that Transformer-based language models outperform conventional bag-of-words and neural models by at least 5% in English and 10% in Turkish for large-scale hate speech detection. The performance is also scalable to different training sizes, such that 98% of performance in English, and 97% in Turkish, are recovered when 20% of training instances are used. We further examine the generalization ability of cross-domain transfer among hate domains. We show that 96% of the performance of a target domain in average is recovered by other domains for English, and 92% for Turkish. Gender and religion are more successful to generalize to other domains, while sports fail most.

show abstract

Section: Methods For Hate Speech Detectionmentioning

confidence: 99%

Section: Methods For Hate Speech Detectionmentioning

confidence: 99%

Large-Scale Hate Speech Detection with Cross-Domain Transfer

Toraman¹,

Şahi̇nuç²,

Yılmaz³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…TEXTBUGGER is a framework that can simulate this type of change. To improve the robustness of the model, the designers improve the dataset, applying scalable simulation methods in the text [7]. The model is based on the LSTM and combined with CNN and attention mechanisms.…”

Section: Enhancing the Robustness Of The Model By Simulating Adversar...mentioning

confidence: 99%

Advanced Deep Learning Approaches for Hate Speech Detection

Wang¹

2023

HSET

View full text Add to dashboard Cite

At present, the influence of social networks on a global scale is increasing, the number of users is increasing significantly, and massive amounts of information are being created every day. How to automatically and efficiently identify harmful information, especially hate speech, has become an important issue in the governance of the network environment. In order to improve the screening efficiency of information containing hate speech, deep learning is applied in this field. Although the research work around this task has made great progress, there are very few reviews on this task, lack of a comprehensive review of the latest development in recent years and can not provide help for researchers who are interested in this task. Therefore, we give an overview of the deep learning applied in hate speech, introducing new ideas for solving this task in recent years, and propose potential problems in the task and analyze it.

show abstract

“…They also developed a framework for securing models against such attacks. Mou et al (2020) proposed to improve the robustness of a hate speech classifier against adversarial attacks by using subword information, wordlevel semantics, and the significance of words calculated by an attention mechanism.…”

Section: Safety and Securitymentioning

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

SWE2: SubWord Enriched and Significant Word Emphasized Framework for Hate Speech Detection

Cited by 11 publications

References 38 publications

Large-Scale Hate Speech Detection with Cross-Domain Transfer

Large-Scale Hate Speech Detection with Cross-Domain Transfer

Advanced Deep Learning Approaches for Hate Speech Detection

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

Contact Info

Product

Resources

About