A literature survey on multimodal and multilingual automatic hate speech identification

Chhabra, Anusha; Vishwakarma, Dinesh Kumar

doi:10.1007/s00530-023-01051-8

Cited by 18 publications

(10 citation statements)

References 114 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we aim to explore these surveys paying more attention to the multilingual aspect of the field. As displayed in Table 1 , some of the existing survey studies focus on presenting definitions and notions related to the domain, as well as an examination of current approaches like in Poletto et al (2021) , Pamungkas, Basile & Patti (2021b) , Chhabra & Vishwakarma (2023) . Meanwhile, other surveys focus on introducing the available sources of the topic, such as data and available source-code ( Vidgen & Derczynski, 2020 ; Poletto et al, 2021 ; Schmidt & Wiegand, 2017 ).…”

Section: Background On Multilingual Hate Speech Phenomenamentioning

confidence: 99%

“…We have carefully studied and analyzed these surveys, which enabled us to construct a comprehensive narrative review in order to cover the deficiencies in these surveys. More specifically, we aim to give an overview of the existing multilingual and cross-lingual approaches, similar to Schmidt & Wiegand (2017) , Yin & Zubiaga (2021) , Fortuna & Nunes (2018) (on English data), to Pamungkas, Basile & Patti (2021b) focusing on cross-lingual methods, as well as Chhabra & Vishwakarma (2023) , where they basically displayed monolingual approaches in some specific languages. Adding to that, some previous surveys have presented existing corpora in the domain, in some specific languages as in Poletto et al (2021) , Jahan & Oussalah (2021) , Chhabra & Vishwakarma (2023) , and more widely in Pamungkas, Basile & Patti (2021b) presenting datasets in 18 different languages, and in Vidgen & Derczynski (2020) , providing an open source website to 63 datasets in multiple languages ( ).…”

Section: Background On Multilingual Hate Speech Phenomenamentioning

confidence: 99%

“…Moreover, few overviews have been conducted on the topic of multilingual offensive language detection, where the survey of Pamungkas, Basile & Patti (2021b) presented the approaches and the available corpora employed in cross-domain and cross-language techniques. Moreover, the survey of Chhabra & Vishwakarma (2023) provided a comprehensive review of hate speech definitions, exploring the essential textual analysis procedures used. The survey also described the advantages and disadvantages of multimodal and cross-lingual approaches.…”

Section: Background On Multilingual Hate Speech Phenomenamentioning

confidence: 99%

See 2 more Smart Citations

A survey on multi-lingual offensive language detection

Mnassri,

Farahbakhsh,

Chalehchaleh

et al. 2024

PeerJ Computer Science

View full text Add to dashboard Cite

The prevalence of offensive content on online communication and social media platforms is growing more and more common, which makes its detection difficult, especially in multilingual settings. The term “Offensive Language” encompasses a wide range of expressions, including various forms of hate speech and aggressive content. Therefore, exploring multilingual offensive content, that goes beyond a single language, focus and represents more linguistic diversities and cultural factors. By exploring multilingual offensive content, we can broaden our understanding and effectively combat the widespread global impact of offensive language. This survey examines the existing state of multilingual offensive language detection, including a comprehensive analysis on previous multilingual approaches, and existing datasets, as well as provides resources in the field. We also explore the related community challenges on this task, which include technical, cultural, and linguistic ones, as well as their limitations. Furthermore, in this survey we propose several potential future directions toward more efficient solutions for multilingual offensive language detection, enabling safer digital communication environment worldwide.

show abstract

Section: Background On Multilingual Hate Speech Phenomenamentioning

confidence: 99%

Section: Background On Multilingual Hate Speech Phenomenamentioning

confidence: 99%

Section: Background On Multilingual Hate Speech Phenomenamentioning

confidence: 99%

See 1 more Smart Citation

A survey on multi-lingual offensive language detection

Mnassri,

Farahbakhsh,

Chalehchaleh

et al. 2024

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…There have been quite a few surveys/reviews on deep learning for the detection of fake news [3], [41], [67] and harmful languages [44]. To the best of our knowledge, standard reviews on multimodal deep learning studies for fake news detection is currently limited to one [25] and none for harmful languages except a survey on general multimodal hate speech detection [19]. This is partly because multimodal studies for both tasks are still emerging rather than being extensive.…”

Section: Related Reviews and Contributionsmentioning

confidence: 99%

A Review of Deep Learning Techniques for Multimodal Fake News and Harmful Languages Detection

Festus Ayetiran,

Özgöbek

2024

IEEE Access

View full text Add to dashboard Cite

The detection of fake news and harmful languages has become increasingly important in today's digital age. As the prevalence of fake news and harmful languages continue to increase, so also is the correspondent negative impact on individuals and the society. Researchers are exploring new techniques to identify and combat these issues. Deep neural network (DNN) has found a wide range of applications in diverse problem domains including but not limited to fake news and harmful languages detection. Fake news and harmful languages are currently increasing online and the mode of dissemination of these contents is fast changing from the traditional unimodal to multiple data forms including texts, audios, images and videos. Multimedia contents containing fake news and harmful languages pose more complex challenges than unimodal contents. The choice and efficacy of the fusion methods of the multimedia contents is one of the most challenging. Our area of focus is multimodal techniques based on deep learning that combines diverse data forms to improve detection accuracy. In this review, we delve into the current state of research, the evolution of deep learning techniques that have been proposed for multimodal fake news and harmful languages detection and the state-of-the-art (SOTA) multimedia data fusion methods. In all cases, we discuss the prospects, relationships, breakthroughs and challenges.

show abstract

“…The United Nations Secretary-General Antonio Guterres recently appealed to the global community to "tackle the hate that spreads like wildfire across the internet" [47]. Owing to this growing threat of hate speech, toxicity classification and hate-speech detection have emerged as important challenges in the machine learning community (See [9,22,32,53,73] for systematic surveys).…”

Section: Introductionmentioning

confidence: 99%

Large image datasets: A pyrrhic win for computer vision?

Birhane

Prabhu²

2021

2021 IEEE Winter Conference on Applications of Computer Vision (WACV)

153

View full text Add to dashboard Cite

Scale the model, scale the data, scale the compute' is the reigning sentiment in the world of generative AI today. While the impact of model scaling has been extensively studied, we are only beginning to scratch the surface of data scaling and its consequences. This is especially of critical importance in the context of visionlanguage datasets such as LAION. These datasets are continually growing in size and are built based on large-scale internet dumps such as the Common Crawl, which is known to have numerous drawbacks ranging from quality, legality, and content. The datasets then serve as the backbone for large generative models, contributing to the operationalization and perpetuation of harmful societal and historical biases and stereotypes. In this paper, we investigate the effect of scaling datasets on hateful content through a comparative audit of two datasets: LAION-400M and LAION-2B. Our results show that hate content increased by nearly 12% with dataset scale, measured both qualitatively and quantitatively using a metric that we term as Hate Content Rate (HCR). We also found that filtering dataset contents based on Not Safe For Work (NSFW) values calculated based on images alone does not exclude all the harmful content in alt-text. Instead, we found that trace amounts of hateful, targeted, and aggressive text remain even when carrying out conservative filtering. We end with a reflection and a discussion of the significance of our results for dataset curation and usage in the AI community. Code and the meta-data assets curated in this paper are publicly available at https://github.com/vinayprabhu/hate_scaling. Content warning: This paper contains examples of hateful text that might be disturbing, distressing, and/or offensive.

show abstract

A literature survey on multimodal and multilingual automatic hate speech identification

Cited by 18 publications

References 114 publications

A survey on multi-lingual offensive language detection

A survey on multi-lingual offensive language detection

A Review of Deep Learning Techniques for Multimodal Fake News and Harmful Languages Detection

Large image datasets: A pyrrhic win for computer vision?

Contact Info

Product

Resources

About