Offensive Text Span Detection in Romanian Comments Using Large Language Models

Author:

Paraschiv Andrei1ORCID,Ion Teodora Andreea2ORCID,Dascalu Mihai12ORCID

Affiliation:

1. Computer Science and Engineering Department, National University of Science and Technology Politehnica of Bucharest, 313 Splaiul Independentei, 060042 Bucharest, Romania

2. Academy of Romanian Scientists, Str. Ilfov, Nr. 3, 050044 Bucharest, Romania

Abstract

The advent of online platforms and services has revolutionized communication, enabling users to share opinions and ideas seamlessly. However, this convenience has also brought about a surge in offensive and harmful language across various communication mediums. In response, social platforms have turned to automated methods to identify offensive content. A critical research question emerges when investigating the role of specific text spans within comments in conveying offensive characteristics. This paper conducted a comprehensive investigation into detecting offensive text spans in Romanian language comments using Transformer encoders and Large Language Models (LLMs). We introduced an extensive dataset of 4800 Romanian comments annotated with offensive text spans. Moreover, we explored the impact of varying model sizes, architectures, and training data volumes on the performance of offensive text span detection, providing valuable insights for determining the optimal configuration. The results argue for the effectiveness of BERT pre-trained models for this span-detection task, showcasing their superior performance. We further investigated the impact of different sample-retrieval strategies for few-shot learning using LLMs based on vector text representations. The analysis highlights important insights and trade-offs in leveraging LLMs for offensive-language-detection tasks.

Publisher

MDPI AG

Subject

Information Systems

Reference67 articles.

1. Sureka, A., and Agarwal, S. (2014, January 24–26). Learning to classify hate and extremism promoting tweets. Proceedings of the 2014 IEEE Joint Intelligence and Security Informatics Conference, The Hague, The Netherlands.

2. Hate in the machine: Anti-Black and Anti-Muslim social media posts as predictors of offline racially and religiously aggravated crime;Williams;Br. J. Criminol.,2020

3. Fanning the flames of hate: Social media and hate crime;Schwarz;J. Eur. Econ. Assoc.,2021

4. Agarwal, S., and Sureka, A. (2015). Applying Social Media Intelligence for Predicting and Identifying On-line Radicalization and Civil Unrest Oriented Threats. arXiv.

5. de Gibert, O., Perez, N., García-Pablos, A., and Cuadros, M. (November, January 31). Hate Speech Dataset from a White Supremacy Forum. Proceedings of the 2nd Workshop on Abusive Language Online (ALW2), Brussels, Belgium.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3