There is a rapid increase in the use of multimedia content in current social media platforms. One of the highly popular forms of such multimedia content are memes. While memes have been primarily invented to promote funny and buoyant discussions, malevolent users exploit memes to target individuals or vulnerable communities, making it imperative to identify and address such instances of hateful memes. Thus social media platforms are in dire need for active moderation of such harmful content. While manual moderation is extremely difficult due to the scale of such content, automatic moderation is challenged by the need of good quality annotated data to train hate meme detection algorithms. This makes a perfect pretext for exploring the power of modern day vision language models (VLMs) that have exhibited outstanding performance across various tasks. In this paper we study the effectiveness of VLMs in handling intricate tasks such as hate meme detection in a completely zero-shot setting so that there is no dependency on annotated data for the task. We perform thorough prompt engineering and query state-of-the-art VLMs using various prompt types to detect hateful/harmful memes. We further interpret the misclassification cases using a novel superpixel based occlusion method. Finally we show that these misclassifications can be neatly arranged into a typology of error classes the knowledge of which should enable the design of better safety guardrails in future. Code and other relevant sources are available online. Warning: Contains potentially offensive content.

Large language models like ChatGPT have recently shown a great promise in performing several tasks, including hate speech detection. However, it is crucial to comprehend the limitations of these models to build robust hate speech detection systems. To bridge this gap, our study aims to evaluate the strengths and weaknesses of the ChatGPT model in detecting hate speech at a granular level across 11 languages. Our evaluation employs a series of functionality tests that reveals various intricate failures of the model which the aggregate metrics like macro F1 or accuracy are not able to unfold. In addition, we investigate the influence of complex emotions, such as the use of emojis in hate speech, on the performance of the ChatGPT model. Our analysis highlights the shortcomings of the generative models in detecting certain types of hate speech and highlighting the need for further research and improvements in the workings of these models.

The dramatic increase in the use of social media platforms for information sharing has also fueled a steep growth in online abuse.A simple yet effective way of abusing individuals or communities is by creating memes, which often integrate an image with a short piece of text layered on top of it.Such harmful elements are in rampant use and are a threat to online safety.Hence it is necessary to develop efficient models to detect and flag abusive memes.The problem becomes more challenging in a low-resource setting (e.g., Bengali memes, i.e., images with Bengali text embedded on it) because of the absence of benchmark datasets on which AI models could be trained.In this paper we bridge this gap by building a Bengali meme dataset.To setup an effective benchmark we implement several baseline models for classifying abusive memes using this dataset 1 .We observe that multimodal models that use both textual and visual information outperform unimodal models.Our best-performing model achieves a macro F1 score of 70.51.Finally, we perform a qualitative error analysis of the misclassified memes of the best-performing text-based, image-based and multimodal models.Disclaimer: This paper contains elements that one might find offensive which cannot be avoided due to the nature of the work.

Hate speech has become one of the most significant issues in modern society, having implications in both the online and the offline world. Due to this, hate speech research has recently gained a lot of traction. However, most of the work has primarily focused on text media with relatively little work on images and even lesser on videos. Thus, early stage automated video moderation techniques are needed to handle the videos that are being uploaded to keep the platform safe and healthy. With a view to detect and remove hateful content from the video sharing platforms, our work focuses on hate video detection using multi-modalities. To this end, we curate ~43 hours of videos from BitChute and manually annotate them as hate or non-hate, along with the frame spans which could explain the labelling decision. To collect the relevant videos we harnessed search keywords from hate lexicons. We observe various cues in images and audio of hateful videos. Further, we build deep learning multi-modal models to classify the hate videos and observe that using all the modalities of the videos improves the overall hate speech detection performance (accuracy=0.798, macro F1-score=0.790) by ~5.7% compared to the best uni-modal model in terms of macro F1 score. In summary, our work takes the first step toward understanding and modeling hateful videos on video hosting platforms such as BitChute.

Hateful content is a growing concern across different platforms, whether it is a moderated platform or an unmoderated platform. The public expression of hate speech encourages the devaluation of minority members. It has some consequences in the real world as well. In such a scenario, it is necessary to design AI systems that could detect such harmful entities/elements in online social media and take cautionary actions to mitigate the risk/harm they cause to society. The way individuals disseminate content on social media platforms also deviates. The content can be in the form of texts, images, videos, etc. Hence hateful content in all forms should be detected, and further actions should be taken to maintain the civility of the platform. We first introduced two published works addressing the challenges of detecting low-resource multilingual abusive speech and hateful user detection. Finally, we discuss our ongoing work on multimodal hateful content detection.

Social media sites such as Twitter and Facebook have connected billions of people and given the opportunity to the users to share their ideas and opinions instantly. That being said, there are several negative consequences as well such as online harassment, trolling, cyber-bullying, fake news, and hate speech. Out of these, hate speech presents a unique challenge as it is deeply engraved into our society and is often linked with offline violence. Social media platforms rely on human moderators to identify hate speech and take necessary action. However, with the increase in online hate speech, these platforms are turning toward automated hate speech detection and mitigation systems. This shift brings several challenges to the plate, and hence, is an important avenue to explore for the computation social science community.

Exploiting social media to spread hate has tremendously increased over the years. Lately, multi-modal hateful content such as memes has drawn relatively more traction than uni-modal content. Moreover, the availability of implicit content payloads makes them fairly challenging to be detected by existing hateful meme detection systems. In this paper, we present a use case study to analyze such systems’ vulnerabilities against external adversarial attacks. We find that even very simple perturbations in uni-modal and multi-modal settings performed by humans with little knowledge about the model can make the existing detection models highly vulnerable. Empirically, we find a noticeable performance drop of as high as 10% in the macro-F1 score for certain attacks. As a remedy, we attempt to boost the model’s robustness using contrastive learning as well as an adversarial training-based method - VILLA. Using an ensemble of the above two approaches, in two of our high resolution datasets, we are able to (re)gain back the performance to a large extent for certain attacks. We believe that ours is a first step toward addressing this crucial problem in an adversarial setting and would inspire more such investigations in the future.

Due to the sheer volume of online hate, the AI and NLP communities have started building models to detect such hateful content. Recently, multilingual hate is a major emerging challenge for automated detection where code-mixing or more than one language have been used for conversation in social media. Typically, hate speech detection models are evaluated by measuring their performance on the held-out test data using metrics such as accuracy and F1-score. While these metrics are useful, it becomes difficult to identify using them where the model is failing, and how to resolve it. To enable more targeted diagnostic insights of such multilingual hate speech models, we introduce a set of functionalities for the purpose of evaluation. We have been inspired to design this kind of functionalities based on real-world conversation on social media. Considering Hindi as a base language, we craft test cases for each functionality. We name our evaluation dataset HateCheckHIn. To illustrate the utility of these functionalities , we test state-of-the-art transformer based m-BERT model and the Perspective API.

Social media platforms were conceived to act as online town squares' where people could get together, share information and communicate with each other peacefully. However, harmful content borne out of bad actors are constantly plaguing these platforms slowly converting them intomosh pits' where the bad actors take the liberty to extensively abuse various marginalised groups. Accurate and timely detection of abusive content on social media platforms is therefore very important for facilitating safe interactions between users. However, due to the small scale and sparse linguistic coverage of Indic abusive speech datasets, development of such algorithms for Indic social media users (one-sixth of global population) is severely impeded.To facilitate and encourage research in this important direction, we contribute for the first time MACD - a large-scale (150K), human-annotated, multilingual (5 languages), balanced (49\% abusive content) and diverse (70K users) abuse detection dataset of user comments, sourced from a popular social media platform - ShareChat. We also release AbuseXLMR, an abusive content detection model pretrained on large number of social media comments in 15+ Indic languages which outperforms XLM-R and MuRIL on multiple Indic datasets. Along with the annotations, we also release the mapping between comment, post and user id's to facilitate modelling the relationship between them. We share competitive monolingual, cross-lingual and few-shot baselines so that MACD can be used as a dataset benchmark for future research.