Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Analysis of Socially Unacceptable Discourse with Zero-shot Learning

Rayane Ghilene, Dimitra Niaouri, Michele Linardi, Julien Longhi

TL;DR

This research investigates the effectiveness of Entailment-based zero-shot text classification (unsupervised method) for SUD detection and characterization by leveraging pre-trained transformer models and prompting techniques.

Abstract

Socially Unacceptable Discourse (SUD) analysis is crucial for maintaining online positive environments. We investigate the effectiveness of Entailment-based zero-shot text classification (unsupervised method) for SUD detection and characterization by leveraging pre-trained transformer models and prompting techniques. The results demonstrate good generalization capabilities of these models to unseen data and highlight the promising nature of this approach for generating labeled datasets for the analysis and characterization of extremist narratives. The findings of this research contribute to the development of robust tools for studying SUD and promoting responsible communication online.

Analysis of Socially Unacceptable Discourse with Zero-shot Learning

TL;DR

This research investigates the effectiveness of Entailment-based zero-shot text classification (unsupervised method) for SUD detection and characterization by leveraging pre-trained transformer models and prompting techniques.

Abstract

Socially Unacceptable Discourse (SUD) analysis is crucial for maintaining online positive environments. We investigate the effectiveness of Entailment-based zero-shot text classification (unsupervised method) for SUD detection and characterization by leveraging pre-trained transformer models and prompting techniques. The results demonstrate good generalization capabilities of these models to unseen data and highlight the promising nature of this approach for generating labeled datasets for the analysis and characterization of extremist narratives. The findings of this research contribute to the development of robust tools for studying SUD and promoting responsible communication online.
Paper Structure (11 sections, 1 figure, 5 tables)

This paper contains 11 sections, 1 figure, 5 tables.

Table of Contents

  1. Introduction
  2. SUD Framework based on Natural Language Inference
  3. Entailment Template
  4. Entailment Models
  5. Empirical Evaluation
  6. Datasets
  7. Evaluation of SUD Classifiers
  8. Template Selection
  9. Results and Discussion
  10. Conclusion and Future Work
  11. References

Figures (1)

  • Figure 1: A piece of text can be assigned labels that describe the different aspects of the text. Relevant labels are in blue. Different characterizations of a hateful stance are at the basis of hate speech analysis DBLP:conf/emnlp/QianBLBW19.