Verbal Abuse Detection from Short Conversations
Abstract
Smart assistants and smart microphones can contribute to detecting verbal abuse by analyzing speech-to-text contents. In this paper, we compare different large language models (LLMs) for detecting verbal abuse and propose a framework that first identifies emotion from short audio conversations by extracting Mel Frequency Cepstral Coefficient (MFCC) and Mel Spectrogram (MEL) features. It then utilizes transfer learning with a fully connected neural network incorporating an attention mechanism and SBERT encoding. To demonstrate the efficacy of the proposed framework, we prepared a custom dataset containing instances of verbal abuse. Evaluation results show that our framework is lightweight and achieves commendable accuracy compared to the existing LLM models.
Department(s)
Computer Science
Document Type
Conference Proceeding
DOI
10.1109/CCNC54725.2025.10976181
Keywords
Attention mechanism, BERT, Emotion detection, K-fold validation, Neural network, SBERT, Transfer learning
Publication Date
1-1-2025
Recommended Citation
Irfan, Fahim Ahmed; Iqbal, Razib; and Behl, Christina, "Verbal Abuse Detection from Short Conversations" (2025). Faculty Scholarship. 237.
https://bearworks.missouristate.edu/articles00/237
Journal Title
Proceedings IEEE Consumer Communications and Networking Conference Ccnc
