“Subverting the Jewtocracy”: Online Antisemitism Detection Using Multimodal Deep Learning

Chandra, Mohit; Pailla, Dheeraj Reddy; Bhatia, Himanshu; Sanchawala, AadilMehdi; Gupta, Manish; Shrivastava, Manish; Kumaraguru, Ponnurangam

doi:10.1145/3447535.3462502

Cited by 19 publications

(19 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

Section: Harmful Memesmentioning

confidence: 98%

“…Figure 1 shows our new typology of harmful content on social media, with focus on memes, which is inspired, but differs, from what was proposed in previous work [Banko et al, 2020;Pramanick et al, 2021a]. For example, [Banko et al, 2020] categorized misinformation as ideological harm, which we excluded from our typology as misinformation is not always harmful. Similarly, while the intent of disinformation is harmful by definition, we do not specifically include it in our typology as most of our sub-categories (e.g., hate and violence) fall under disinformation .…”

Section: Harmful Memesmentioning

confidence: 98%

“…Such content can target individuals, communities, and companies. Social media have defined various categories of harmful content that they do not allow on their platforms [Halevy et al, 2022;, and various categorizations have come from the research community [Banko et al, 2020;Pramanick et al, 2021a].…”

Section: Introductionmentioning

confidence: 99%

“…More generally, some of the latest surveys on specific aspects of violating content have been on detecting fake news [Thorne and Vlachos, 2018;Islam et al, 2020;Kotonya and Toni, 2020], disinformation Hardalov et al, 2022], misinformation Nakov et al, 2021c], rumours [Bondielli and Marcelloni, 2019], propaganda [Da San Martino et al, 2020], memes [Afridi et al, 2021], hate speech [Fortuna and Nunes, 2018;Schmidt and Wiegand, 2017], cyberbullying [Haidar et al, 2016], and offensive content [Husain and Uzuner, 2021].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Detecting and Understanding Harmful Memes: A Survey

Teeti

Khan

Shahbaz

et al. 2022

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

This survey targets intention and trajectory prediction in Autonomous Vehicles (AV), as AV companies compete to create dedicated prediction pipelines to avoid collisions. The survey starts with a formal definition of the prediction problem and highlights its challenges, to then critically compare the models proposed in the last 2-3 years in terms of how they overcome these challenges. Further, it lists the latest methodological and technical trends in the field and comments on the efficacy of different machine learning blocks in modelling various aspects of the prediction problem. It also summarises the popular datasets and metrics used to evaluate prediction models, before concluding with the possible research gaps and future directions.

show abstract

Section: Harmful Memesmentioning

confidence: 98%

Section: Harmful Memesmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Detecting and Understanding Harmful Memes: A Survey

Teeti

Khan

Shahbaz

et al. 2022

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…Having observed the exceptional performance of these Transformer based models, we also utilize a Transformer based model, MURIL, which is pre-trained explicitly in Indian Languages. (Pramanick et al, 2021;Chandra et al, 2021).…”

Section: Text-based Abusive Content Detectionmentioning

confidence: 99%

hate-alert@DravidianLangTech-ACL2022: Ensembling Multi-Modalities for Tamil TrollMeme Classification

Das¹,

Banerjee²,

Mukherjee³

2022

Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages

View full text Add to dashboard Cite

Social media platforms often act as breeding grounds for various forms of trolling or malicious content targeting users or communities. One way of trolling users is by creating memes, which in most cases unites an image with a short piece of text embedded on top of it. The situation is more complex for multilingual(e.g., Tamil) memes due to the lack of benchmark datasets and models. We explore several models to detect Troll memes in Tamil based on the shared task, "Troll Meme Classification in DravidianLangTech2022" at ACL-2022. We observe while the text-based model MURIL performs better for Non-troll meme classification, the image-based model VGG16 performs better for Troll-meme classification. Further fusing these two modalities help us achieve stable outcomes in both classes. Our fusion model achieved a 0.561 weighted average F1 score and ranked second in this task.

show abstract

Health, Religiosity and Hatred: A Study of the Impacts of COVID-19 on World Jewry

2022

View full text Add to dashboard Cite

This exploratory study examines the likely causes of the alarming global rise of antisemitism during the COVID-19 pandemic. Beginning with an appraisal of today's world Jewry, this exploratory study highlights the main social, health, and religious impacts COVID-19 has had on Jews worldwide and goes on to highlight how various Jewish communities managed and adjusted to COVID-19 public health restrictions. From this contextual backdrop, an assessment of how and why antisemitism has surged during the pandemic is presented, along with a review of what efforts are being taken to curtail this rise in hatred toward Jews. A central aim of this study is to underline the point that until meaningful, broad, and international steps are taken to curb online hate, the historic antisemitic tropes and myths suggesting Jews are the cause of disease will undoubtedly evolve and surge (especially across social media) during future pandemics and times of global crisis and unrest.

show abstract

“Subverting the Jewtocracy”: Online Antisemitism Detection Using Multimodal Deep Learning

Cited by 19 publications

References 19 publications

Detecting and Understanding Harmful Memes: A Survey

Detecting and Understanding Harmful Memes: A Survey

hate-alert@DravidianLangTech-ACL2022: Ensembling Multi-Modalities for Tamil TrollMeme Classification

Health, Religiosity and Hatred: A Study of the Impacts of COVID-19 on World Jewry

Contact Info

Product

Resources

About