Assessing In-context Learning and Fine-tuning for Topic Classification of German Web Data

Julian Schelb, Andreas Spitz, Roberto Ulloa


Abstract
Researchers in the political and social sciences often rely on classification models to analyze trends in information consumption by examining browsing histories of millions of webpages. Automated scalable methods are necessary due to the impracticality of manual labeling. In this paper, we model the detection of topic-related content as a binary classification task and compare the accuracy of fine-tuned pre-trained encoder models against in-context learning strategies. Using only a few hundred annotated data points per topic, we detect content related to three German policies in a database of scraped webpages. We compare multilingual and monolingual models, as well as zero and few-shot approaches, and investigate the impact of negative sampling strategies and the combination of URL & content-based features. Our results show that a small sample of annotated data is sufficient to train an effective classifier. Fine-tuning encoder-based models yields better results than in-context learning. Classifiers using both URL & content-based features perform best, while using URLs alone provides adequate results when content is unavailable.
Anthology ID:
2024.acl-srw.22
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Xiyan Fu, Eve Fleisig
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
144–158
Language:
URL:
https://aclanthology.org/2024.acl-srw.22
DOI:
10.18653/v1/2024.acl-srw.22
Bibkey:
Cite (ACL):
Julian Schelb, Andreas Spitz, and Roberto Ulloa. 2024. Assessing In-context Learning and Fine-tuning for Topic Classification of German Web Data. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 144–158, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Assessing In-context Learning and Fine-tuning for Topic Classification of German Web Data (Schelb et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-srw.22.pdf