Neural Word Decomposition Models for Abusive Language Detection

Bodapati, Sravan; Gella, Spandana; Bhattacharjee, Kasturi; Al-Onaizan, Yaser

doi:10.18653/v1/w19-3515

Cited by 25 publications

(22 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For Wikipedia, Bodapati et al (2019) report the weighted F1 of 95.7 as the state-of-the-art results. However, when we re-implement their model, we achieve a slightly better weighted F1 of 95.9 as what we report in Table 5.…”

Section: Classification Resultsmentioning

confidence: 99%

“…This model includes an ensemble of several machine learning classifier with word n-grams and character n-grams lexical features. 8 Bodapati'19 (Bodapati et al, 2019): This work reported the state-of-the-art results on the Wikipedia dataset. The authors added a single dense layer on top of BERT to fine-tune it for the task of abusive language detection.…”

Section: Baselines and Sota Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Attending the Emotions to Detect Online Abusive Language

Samghabadi¹,

Hatami²,

Shafaei³

et al. 2020

Proceedings of the Fourth Workshop on Online Abuse and Harms

View full text Add to dashboard Cite

In recent years, abusive behavior has become a serious issue in online social networks. In this paper, we present a new corpus for the task of abusive language detection that is collected from a semi-anonymous online platform, and unlike the majority of other available resources, is not created based on a specific list of bad words. We also develop computational models to incorporate emotions into textual cues to improve aggression identification. We evaluate our proposed methods on a set of corpora related to the task and show promising results with respect to abusive language detection.

show abstract

Section: Classification Resultsmentioning

confidence: 99%

Section: Baselines and Sota Approachesmentioning

confidence: 99%

Attending the Emotions to Detect Online Abusive Language

Samghabadi¹,

Hatami²,

Shafaei³

et al. 2020

Proceedings of the Fourth Workshop on Online Abuse and Harms

View full text Add to dashboard Cite

show abstract

“…Several ideas have been proposed in the literature to improve the performance of BERT for abusive language detection. For example, finetuning large pre-trained language models in (Bodapati et al, 2019).…”

Section: Related Workmentioning

confidence: 99%

HurtBERT: Incorporating Lexical Features with BERT for the Detection of Abusive Language

Koufakou¹,

Pamungkas²,

Basile³

et al. 2020

Proceedings of the Fourth Workshop on Online Abuse and Harms

View full text Add to dashboard Cite

The detection of abusive or offensive remarks in social texts has received significant attention in research. In several related shared tasks, BERT has been shown to be the state-of-theart. In this paper, we propose to utilize lexical features derived from a hate lexicon towards improving the performance of BERT in such tasks. We explore different ways to utilize the lexical features in the form of lexicon-based encodings at the sentence level or embeddings at the word level. We provide an extensive dataset evaluation that addresses in-domain as well as cross-domain detection of abusive content to render a complete picture. Our results indicate that our proposed models combining BERT with lexical features help improve over a baseline BERT model in many of our indomain and cross-domain experiments.

show abstract

“…Long Short Term Memory (LSTM) model [13] or Gated Recurrent Unit (GRU) model [14] capture the long range dependencies. Such properties are important for modelling toxic speech [7], [15].…”

Section: She Looks Like a Plastic Monkey Doll!mentioning

confidence: 99%

BERT and fastText Embeddings for Automatic Detection of Toxic Speech

D'Sa

Illina

Fohr

2020

2020 International Multi-Conference On: “Organization of Knowledge and Advanced Technologies” (OCTA)

View full text Add to dashboard Cite

With the expansion of Internet usage, catering to the dissemination of thoughts and expressions of an individual, there has been an immense increase in the spread of online hate speech. Social media, community forums, discussion platforms are few examples of common playground of online discussions where people are freely allowed to communicate. However, the freedom of speech may be misused by some people by arguing aggressively, offending others and spreading verbal violence. As there is no clear distinction between the terms offensive, abusive, hate and toxic speech, in this paper we consider the above mentioned terms as toxic speech. In many countries, online toxic speech is punishable by the law. Thus, it is important to automatically detect and remove toxic speech from online medias. Through this work, we propose automatic classification of toxic speech using embedding representations of words and deep-learning techniques. We perform binary and multi-class classification using a Twitter corpus and study two approaches: (a) a method which consists in extracting of word embeddings and then using a DNN classifier; (b) fine-tuning the pre-trained BERT model. We observed that BERT fine-tuning performed much better. Proposed methodology can be used for any other type of social media comments.

show abstract

Neural Word Decomposition Models for Abusive Language Detection

Cited by 25 publications

References 29 publications

Attending the Emotions to Detect Online Abusive Language

Attending the Emotions to Detect Online Abusive Language

HurtBERT: Incorporating Lexical Features with BERT for the Detection of Abusive Language

BERT and fastText Embeddings for Automatic Detection of Toxic Speech

Contact Info

Product

Resources

About