SAINT: Multilingual Span-Level Interpretability for Sentiment Analysis

Seid Muhie Yimam, Tadesse Destaw Belay, Robert Geislinger, Shamsuddeen Hassan Muhammad, Adaeze Ngozi Ohuoba, Sukairaj Hafiz Imam, Abinew Ali Ayele, Martin Semmann, Chris Biemann, Serge Sharoff


Abstract
We investigate multilingual sentiment analysis and interpretability across high- and low-resource languages, focusing on Amharic, English, German, and Hausa. Our study evaluates encoder-only transformer models for both sequence-level sentiment classification and token-level attribution using Captum. Additionally, we assess zero- and few-shot decoder-only models for sequence-level sentiment prediction. Our results show that few-shot decoder-only models outperform encoder-only models on token-level sentiment classification in most languages, with the exception of Hausa, where a multilingual encoder-based model leads. For sequence-level sentiment classification, encoder-only models generally achieve strong performance across most languages, but decoder-only models are highly competitive, and may even surpass encoders, in the high-resource settings (German, English) and low-resource scenarios, depending on the prompting strategy. These findings highlight the utility of combining fine-tuned transformer models with prompt- based large language models to build interpretable sentiment analysis systems across both low- and high-resource languages. The SAINT dataset, annotation guideline, and evaluation scripts can be found at https://github.com/uhh-hcds/SAINT.
Anthology ID:
2026.sigul-1.6
Volume:
Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages
Month:
May
Year:
2026
Address:
Palma, Mallorca, Spain
Editors:
Atul Kr. Ojha, Sakriani Sakti, Claudia Soria, Maite Melero, John P. McCrae, Constantine Lignos, Chao-Hong Liu, German Rigau Claramunt, Georg Rehm
Venues:
SIGUL | EURALI | DCLRL | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
54–65
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-sigul-06
DOI:
10.63317/2ph93cb2qi57
Bibkey:
Cite (ACL):
Seid Muhie Yimam, Tadesse Destaw Belay, Robert Geislinger, Shamsuddeen Hassan Muhammad, Adaeze Ngozi Ohuoba, Sukairaj Hafiz Imam, Abinew Ali Ayele, Martin Semmann, Chris Biemann, and Serge Sharoff. 2026. SAINT: Multilingual Span-Level Interpretability for Sentiment Analysis. In Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages, pages 54–65, Palma, Mallorca, Spain. ELRA Language Resources Association (ELRA).
Cite (Informal):
SAINT: Multilingual Span-Level Interpretability for Sentiment Analysis (Yimam et al., SIGUL-EURALI-DCLRL 2026)
Copy Citation: