Mind Your Language: Abuse and Offense Detection for Code-Switched Languages

Kapoor, Raghav; Kumar, Yaman; Rajput, Kshitij; Shah, Rajiv Ratn; Kumaraguru, Ponnurangam; Zimmermann, Roger

doi:10.1609/aaai.v33i01.33019951

Cited by 17 publications

(11 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To understand the racial and dialectic bias in toxic language detection, we focus our analyses on two corpora of tweets (Davidson et al, 2017;Founta et al, 2018) that are widely used in hate speech detection (Park et al, 2018;van Aken et al, 2018;Kapoor et al, 2018;Alorainy et al, 2018 DWMW17 (Davidson et al, 2017) includes annotations of 25K tweets as hate speech, offensive (but not hate speech), or none. The authors collected data from Twitter, starting with 1,000 terms from HateBase (an online database of hate speech terms) as seeds, and crowdsourced at least three annotations per tweet.…”

Section: Biases In Toxic Language Datasetsmentioning

confidence: 99%

The Risk of Racial Bias in Hate Speech Detection

Sap

Card

Gabriel

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

579

559

View full text Add to dashboard Cite

We investigate how annotators' insensitivity to differences in dialect can lead to racial bias in automatic hate speech detection models, potentially amplifying harm against minority populations. We first uncover unexpected correlations between surface markers of African American English (AAE) and ratings of toxicity in several widely-used hate speech datasets. Then, we show that models trained on these corpora acquire and propagate these biases, such that AAE tweets and tweets by self-identified African Americans are up to two times more likely to be labelled as offensive compared to others. Finally, we propose dialect and race priming as ways to reduce the racial bias in annotation, showing that when annotators are made explicitly aware of an AAE tweet's dialect they are significantly less likely to label the tweet as offensive.

show abstract

Section: Biases In Toxic Language Datasetsmentioning

confidence: 99%

The Risk of Racial Bias in Hate Speech Detection

Sap

Card

Gabriel

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

579

559

View full text Add to dashboard Cite

show abstract

“…On a similar direction there has been work on understanding the main intentions behind vulgar expressions in social media (Holgate et al, 2018). Various approaches have been taken to tackle both textual as well as multimodal data from Twitter and social media in general, in order to build deep learning classifiers for similar tasks (Baghel et al, 2018;Kapoor et al, 2018;Mahata et al, 2018a,b;Jangid et al, 2018;Meghawat et al, 2018;Shah and Zimmermann, 2017). The dataset provided for the tasks was collected through Twitter API by searching for tweets containing certain selected keyword patterns popular in offensive posts.…”

Section: Related Workmentioning

confidence: 99%

MIDAS at SemEval-2019 Task 6: Identifying Offensive Posts and Targeted Offense from Twitter

Mahata¹,

Zhang²,

Uppal³

et al. 2019

Proceedings of the 13th International Workshop on Semantic Evaluation

Self Cite

View full text Add to dashboard Cite

In this paper, we present our approach and the system description for Sub-task A and Sub Task B of SemEval 2019 Task 6: Identifying and Categorizing Offensive Language in Social Media. Sub-task A involves identifying if a given tweet is offensive or not, and Sub Task B involves detecting if an offensive tweet is targeted towards someone (group or an individual). Our models for Sub-task A is based on an ensemble of Convolutional Neural Network, Bidirectional LSTM with attention, and Bidirectional LSTM + Bidirectional GRU, whereas for Sub-task B, we rely on a set of heuristics derived from the training data and manual observation. We provide a detailed analysis of the results obtained using the trained models. Our team ranked 5th out of 103 participants in Sub-task A, achieving a macro F1 score of 0.807, and ranked 8th out of 75 participants in Sub Task B achieving a macro F1 of 0.695.

show abstract

“…Yet, recent works exhibit efforts towards the diversification of the objects of study. Datasets are created for less-studied languages such as Hinglish [61,139], Bengali [147], and Arabic [62,123], revealing new challenges pertaining to the particular language structures (e.g., in Hinglish, the grammar is not fixed, the written words use Roman script for spoken works in Hindi [139], a list of challenges for Arabic is proposed in Al-Hassan et al [5]); and for less-common social media platforms (e.g., YouTube comments [62,147]).…”

Section: Data Retrievalmentioning

confidence: 99%

Automatic Identification of Harmful, Aggressive, Abusive, and Offensive Language on the Web: A Survey of Technical Biases Informed by Psychology Literature

Balayn

Yang

Szlávik

et al. 2021

Trans. Soc. Comput.

View full text Add to dashboard Cite

The automatic detection of conflictual languages (harmful, aggressive, abusive, and offensive languages) is essential to provide a healthy conversation environment on the Web. To design and develop detection systems that are capable of achieving satisfactory performance, a thorough understanding of the nature and properties of the targeted type of conflictual language is of great importance. The scientific communities investigating human psychology and social behavior have studied these languages in details, but their insights have only partially reached the computer science community. In this survey, we aim both at systematically characterizing the conceptual properties of online conflictual languages, and at investigating the extent to which they are reflected in state-of-the-art automatic detection systems. Through an analysis of psychology literature, we provide a reconciled taxonomy that denotes the ensemble of conflictual languages typically studied in computer science. We then characterize the conceptual mismatches that can be observed in the main semantic and contextual properties of these languages and their treatment in computer science works; and systematically uncover resulting technical biases in the design of machine learning classification models and the dataset created for their training. Finally, we discuss diverse research opportunities for the computer science community and reflect on broader technical and structural issues.

show abstract

Mind Your Language: Abuse and Offense Detection for Code-Switched Languages

Cited by 17 publications

References 3 publications

The Risk of Racial Bias in Hate Speech Detection

The Risk of Racial Bias in Hate Speech Detection

MIDAS at SemEval-2019 Task 6: Identifying Offensive Posts and Targeted Offense from Twitter

Automatic Identification of Harmful, Aggressive, Abusive, and Offensive Language on the Web: A Survey of Technical Biases Informed by Psychology Literature

Contact Info

Product

Resources

About