Multilingual Target-Stance Extraction

Ethan Leigh Mines, Bonnie J. Dorr


Abstract
Social media enables data-driven analysis of public opinion on contested issues. Target-Stance Extraction (TSE) is the task of identifying the target discussed in a document and the document’s stance towards that target. Many works classify stance towards a given target in a multilingual setting, but all prior work in TSE is English-only. This work introduces the first multilingual TSE benchmark, spanning Catalan, Estonian, French, Italian, Mandarin, and Spanish corpora. It manages to extend the original TSE pipeline to a multilingual setting without requiring separate models for each language. Our model pipeline achieves a modest F1 score of 12.78, underscoring the increased difficulty of the multilingual task relative to English-only setups and highlighting target prediction as the primary bottleneck. We are also the first to demonstrate the sensitivity of TSE’s F1 score to different target verbalizations. Together these serve as a much-needed baseline for resources, algorithms, and evaluation criteria in multilingual TSE.
Anthology ID:
2026.lrec-1.707
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
8997–9007
Language:
External URL:
https://lrec.elra.info/lrec2026-main-707
DOI:
10.63317/3q975uotc5m6
Bibkey:
Cite (ACL):
Ethan Leigh Mines and Bonnie J. Dorr. 2026. Multilingual Target-Stance Extraction. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 8997–9007, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
Multilingual Target-Stance Extraction (Mines & Dorr, LREC 2026)
Copy Citation:
Optionalsupplementarymaterial:
 2026.lrec-1.707.OptionalSupplementaryMaterial.zip