Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.11851/10978
Full metadata record
DC FieldValueLanguage
dc.contributor.authorZengin, Muhammed Said-
dc.contributor.authorYenisey, Berk Utku-
dc.contributor.authorKutlu, Mucahid-
dc.date.accessioned2024-01-21T09:24:24Z-
dc.date.available2024-01-21T09:24:24Z-
dc.date.issued2023-
dc.identifier.issn1300-0632-
dc.identifier.issn1303-6203-
dc.identifier.urihttps://doi.org/10.55730/1300-0632.4043-
dc.identifier.urihttps://hdl.handle.net/20.500.11851/10978-
dc.description.abstractStance detection has garnered considerable attention from researchers due to its broad range of applications, including fact-checking and social computing. While state-of-the-art stance detection models are usually based on supervised machine learning methods, their effectiveness is heavily reliant on the quality of training data. This problem is more prevalent in stance detection task because the stance of a text is intimately tied to the target under consideration. While numerous datasets exist for stance detection, determining their suitability for a specific target can be challenging. In this work, we focus on Turkish stance detection and explore the impact of training data on the model performance. In particular, we fine-tune BERT model with various datasets and assess their performance when the test data is the same/different compared to the training data in terms of target and domain. In addition, given the scarcity of resources for Turkish stance detection, we investigate i) whether we can use existing datasets in other languages in a cross-lingual setup, and ii) the effectiveness of data augmentation with simple automatic labeling methods. In order to conduct our experiments, we also create new Turkish stance detection datasets for various targets in different domains. In our comprehensive experiments, our findings are as follows. 1) Using training data with multiple targets in the same domain yields high performance as the model is able to learn more characteristics of expressing stance with additional data. 2) The domain of the training data plays a crucial role in achieving high performance. 3) Automatically generated data enhances performance when combined with manually annotated data. 4) Training solely on Turkish data outperforms training with the combination of Turkish and English data. Overall, our study points out the importance of creating Turkish annotated datasets for different domains to achieve high performance in stance detection.en_US
dc.description.sponsorshipScientific and Technological Research Council of Tuerkiye (TUBITAK) [ARDEB 3501, 120E514]en_US
dc.description.sponsorshipThis study was funded by the Scientific and Technological Research Council of Tuerkiye (TUBITAK) ARDEB 3501 Grant No 120E514. The statements made herein are solely the responsibility of the authors.en_US
dc.language.isoenen_US
dc.publisherTubitak Scientific & Technological Research Council Turkeyen_US
dc.relation.ispartofTurkish Journal of Electrical Engineering and Computer Sciencesen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectStance detectionen_US
dc.subjectnatural language processingen_US
dc.subjectTurkishen_US
dc.titleExploring the Impact of Training Datasets on Turkish Stance Detectionen_US
dc.typeArticleen_US
dc.departmentTOBB ETÜen_US
dc.identifier.volume31en_US
dc.identifier.issue7en_US
dc.identifier.startpage1206en_US
dc.identifier.endpage1222en_US
dc.identifier.wosWOS:001115009000006en_US
dc.identifier.scopus2-s2.0-85180009303en_US
dc.institutionauthor-
dc.identifier.doi10.55730/1300-0632.4043-
dc.authorscopusid57226399864-
dc.authorscopusid58769223300-
dc.authorscopusid35299304300-
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.identifier.trdizinid1220953en_US
item.openairetypeArticle-
item.languageiso639-1en-
item.grantfulltextnone-
item.fulltextNo Fulltext-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.cerifentitytypePublications-
crisitem.author.dept02.3. Department of Computer Engineering-
Appears in Collections:Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection
Show simple item record



CORE Recommender

WEB OF SCIENCETM
Citations

1
checked on Aug 31, 2024

Page view(s)

84
checked on Dec 23, 2024

Google ScholarTM

Check




Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.