Hellwig, Nils Constantin and Fehle, Jakob and Wolff, Christian (2025) Exploring large language models for the generation of synthetic training samples for aspect-based sentiment analysis in low resource settings. EXPERT SYSTEMS WITH APPLICATIONS, 261: 125514. ISSN 0957-4174, 1873-6793
Full text not available from this repository. (Request a copy)Abstract
Aspect-Based Sentiment Analysis (ABSA) is a fine-grained task in sentiment analysis, aiming to identify sentiment expressed towards specific aspects of an entity. This paper explores the use of Large Language Models (LLMs), specifically GPT-3.5-turbo and Llama-3-70B, for generating annotated data in Aspect-Based Sentiment Analysis (ABSA), aiming to address the scarcity of labelled datasets in the field. Two low-resource scenarios are considered, with 25 and 500 manually annotated examples available. In the 25-example scenario, adding synthetic examples generated through few-shot prompting resulted in F1 scores of 81.33 for Aspect Category Detection (ACD) and 71.71 for Aspect Category Sentiment Analysis (ACSA). For the 500-example scenario, synthetic data augmentation showed a notable gain only for the ACSA task, raising the F1 score from 84.54 to 86.70.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | ; Natural language processing (NLP); Sentiment analysis (SA); Aspect-based sentiment analysis (ABSA); Large language models (LLMs); Synthetic data generation; Low-resource settings; Data augmentation |
| Subjects: | 000 Computer science, information & general works > 004 Computer science |
| Divisions: | Languages and Literatures > Institut für Information und Medien, Sprache und Kultur (I:IMSK) > Lehrstuhl für Medieninformatik (Prof. Dr. Christian Wolff) Informatics and Data Science > Department Human-Centered Computing > Lehrstuhl für Medieninformatik (Prof. Dr. Christian Wolff) |
| Depositing User: | Dr. Gernot Deinzer |
| Date Deposited: | 03 Mar 2026 09:22 |
| Last Modified: | 03 Mar 2026 09:22 |
| URI: | https://pred.uni-regensburg.de/id/eprint/63543 |
Actions (login required)
 |
View Item |
