# Multilingual and Multimodal Abuse Detection

arXiv: https://arxiv.org/abs/2204.02263 · HTML: https://mlsanity.com/paper/2204.02263/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 37 references that are in the map.
- First posted on arXiv 3 Apr 2022.

## Builds on (most cited first, 14 of 14)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Unsupervised Cross-lingual Representation Learning for Speech Recognition](https://mlsanity.com/paper/2006.13979/) (2020)
- [Unsupervised Speech Recognition](https://mlsanity.com/paper/2105.11084/) (2021)
- [KUISAIL at SemEval-2020 Task 12: BERT-CNN for Offensive Speech Identification in Social Media](https://mlsanity.com/paper/2007.13184/) (2020)
- [One-step and Two-step Classification for Abusive Language Detection on Twitter](https://mlsanity.com/paper/1706.01206/) (2017)
- [CLSRIL-23: Cross Lingual Speech Representations for Indic Languages](https://mlsanity.com/paper/2107.07402/) (2021)
- [Emotion Based Hate Speech Detection using Multimodal Learning](https://mlsanity.com/paper/2202.06218/) (2022)
- [Joint Modelling of Emotion and Abusive Language Detection](https://mlsanity.com/paper/2005.14028/) (2020)
- [Mind Your Language: Abuse and Offense Detection for Code-Switched Languages](https://mlsanity.com/paper/1809.08652/) (2018)
- [ADIMA: Abuse Detection In Multilingual Audio](https://mlsanity.com/paper/2202.07991/) (2022)
- [Offensive Language and Hate Speech Detection with Deep Learning and Transfer Learning](https://mlsanity.com/paper/2108.03305/) (2021)
- [Toxicity Detection for Indic Multilingual Social Media Content](https://mlsanity.com/paper/2201.00598/) (2022)

## Abstract (arXiv)

The presence of abusive content on social media platforms is undesirable as it severely impedes healthy and safe social media interactions. While automatic abuse detection has been widely explored in textual domain, audio abuse detection still remains unexplored. In this paper, we attempt abuse detection in conversational audio from a multimodal perspective in a multilingual social media setting. Our key hypothesis is that along with the modelling of audio, incorporating discriminative information from other modalities can be highly beneficial for this task. Our proposed method, MADA, explicitly focuses on two modalities other than the audio itself, namely, the underlying emotions expressed in the abusive audio and the semantic information encapsulated in the corresponding textual form. Observations prove that MADA demonstrates gains over audio-only approaches on the ADIMA dataset. We test the proposed approach on 10 different languages and observe consistent gains in the range 0.6%-5.2% by leveraging multiple modalities. We also perform extensive ablation experiments for studying the contributions of every modality and observe the best results while leveraging all the modalities together. Additionally, we perform experiments to empirically confirm that there is a strong correlation between underlying emotions and abusive behaviour.