JOURNAL ARTICLE

Detecting multilingual hate speech targeting immigrants and women on Twitter.

  • Published In: Journal of Intelligent & Fuzzy Systems, 2026, v. 50, n. 2. P. 348 1 of 3

  • Database: Academic Search Ultimate 2 of 3

  • Authored By: Kolesnikova, Olga; Yigezu, Mesay Gemeda; Gelbukh, Alexander; Abitte, Selam; Sidorov, Grigori 3 of 3

Abstract

This article focuses on detecting hate speech (HS) and aggressive behavior (AB) on social media, particularly targeting immigrants and women, using deep learning techniques. It proposes an ensemble approach combining Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), Convolutional Neural Networks (CNN), and Gated Recurrent Units (GRU) models to improve classification accuracy across English, Spanish, and multilingual datasets. The study employs data balancing methods such as random under-sampling and over-sampling to address class imbalance and reports that the ensemble model achieves superior F1 scores (up to 0.97) compared to individual models. Future work includes exploring pretrained models and advanced data augmentation and balancing techniques to further enhance detection performance.

Additional Information

  • Source:Journal of Intelligent & Fuzzy Systems. 2026/02, Vol. 50, Issue 2, p348
  • Document Type:Article
  • Subject Area:Social Sciences and Humanities
  • Publication Date:2026
  • ISSN:1064-1246
  • DOI:10.3233/JIFS-219350
  • Accession Number:192308524
  • Copyright Statement:Copyright of Journal of Intelligent & Fuzzy Systems is the property of Sage Publications Inc. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Looking to go deeper into this topic? Look for more articles on EBSCOhost.