Digitala Vetenskapliga Arkivet

Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Enhancing social media hate speech detection in low-resource languages using transformers and explainable AI
University of Prizren, Kosovo.
University of Prizren, Kosovo.
South East European University, North Macedonia.
Linnaeus University, Faculty of Technology, Department of Informatics. Linnaeus University, Linnaeus Knowledge Environments, Digital Transformations.ORCID iD: 0000-0002-0199-2377
Show others and affiliations
2025 (English)In: Social Network Analysis and Mining, ISSN 1869-5450, E-ISSN 1869-5469, Vol. 15, article id 82Article in journal (Refereed) Published
Abstract [en]

Hate speech (HS) on social media exposes public discourse and community well-being. Despite its prevalence, majority of the research and technological advances have focused on rich-resourced languages. In contrast, Albanian, a language marked by dialects, limited NLP tools, and scarcity of annotated data, remains underexplored. To address this gap, this paper explores the enhancement of automatic hate speech detection in Albanian social media using advanced deep neural techniques. We collected a real-life dataset comprising 20,860 Facebook comments manually annotated using a rigorous multi-annotator process. Various techniques, including machine learning, deep neural networks, and transformers, are tested on the collected dataset. Our findings show that character-level 4-gram TF-IDF consistently reinforces ML classifiers effective with informal spelling and slang. However, the fine-tuned transformer XLM-RoBERTa achieves the highest performance with an F1-score up to 86%. These results mark a new benchmark for Albanian HS detection and highlight the impact of thorough feature engineering and robust representation techniques in a low-resource context. We also carried out an error analysis using both manual inspection and explainable AI approaches such as SHAP and LIME. Key language challenges include dialectal writing, short sentences, and implicit insults. These insights highlight the importance of domain-aligned embedding resources, more extensive annotation, and fine-grained context handling for improved detection. This study establishes a new state-of-the-art result for Albanian hate speech detection, provides a valuable comparison of models and feature engineering, and underscores the potential of multilingual transformers in low-resource scenarios.

Place, publisher, year, edition, pages
Springer, 2025. Vol. 15, article id 82
Keywords [en]
Social media, Hate speech, Transformers, Machine learning, Deep learning, Feature engineering, Explainable AI (XAI)
National Category
Computer Sciences Natural Language Processing
Research subject
Computer and Information Sciences Computer Science, Information Systems
Identifiers
URN: urn:nbn:se:lnu:diva-141052DOI: 10.1007/s13278-025-01497-wISI: 001541394900003Scopus ID: 2-s2.0-105014110779OAI: oai:DiVA.org:lnu-141052DiVA, id: diva2:1988516
Available from: 2025-08-12 Created: 2025-08-12 Last updated: 2026-04-16Bibliographically approved

Open Access in DiVA

fulltext(2193 kB)404 downloads
File information
File name FULLTEXT01.pdfFile size 2193 kBChecksum SHA-512
52fc2f0caeac560c1a0496af01821a47c8d8fc8580591085d3d608458b97195264db59437be1bccdb3e88bb5f11eb66545fff5b09d5b2b1a7a7fd33bda118e75
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Kastrati, Zenun
By organisation
Department of InformaticsDigital Transformations
In the same journal
Social Network Analysis and Mining
Computer SciencesNatural Language Processing

Search outside of DiVA

GoogleGoogle Scholar
Total: 406 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 259 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf