AGCL: Aspect Graph Construction and Learning for Aspect-level Sentiment Classification
Issued Date
2025-01-01
Resource Type
ISSN
29512093
Scopus ID
2-s2.0-85218503649
Journal Title
Proceedings - International Conference on Computational Linguistics, COLING
Volume
Part F206484-1
Start Page
841
End Page
854
Rights Holder(s)
SCOPUS
Bibliographic Citation
Proceedings - International Conference on Computational Linguistics, COLING Vol.Part F206484-1 (2025) , 841-854
Suggested Citation
Jian Z., Wu D., Wang S., Wang Y., Yao J., Wang M., Wu Q. AGCL: Aspect Graph Construction and Learning for Aspect-level Sentiment Classification. Proceedings - International Conference on Computational Linguistics, COLING Vol.Part F206484-1 (2025) , 841-854. 854. Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/105501
Title
AGCL: Aspect Graph Construction and Learning for Aspect-level Sentiment Classification
Author's Affiliation
Corresponding Author(s)
Other Contributor(s)
Abstract
Prior studies on Aspect-level Sentiment Classification (ALSC) emphasize modeling interrelationships among aspects and contexts but overlook the crucial role of aspects themselves as essential domain knowledge. To this end, we propose AGCL, a novel Aspect Graph Construction and Learning method, aimed at furnishing the model with finely tuned aspect information to bolster its task-understanding ability. AGCL's pivotal innovations reside in Aspect Graph Construction (AGC) and Aspect Graph Learning (AGL), where AGC harnesses intrinsic aspect connections to construct the domain aspect graph, and then AGL iteratively updates the introduced aspect graph to enhance its domain expertise, making it more suitable for the ALSC task. Hence, this domain aspect graph can serve as a bridge connecting unseen aspects with seen aspects, thereby enhancing the model's generalization capability. Experiment results on three widely used datasets demonstrate the significance of aspect information for ALSC and highlight AGL's superiority in aspect learning, surpassing state-of-the-art baselines greatly. Code is available at https://github.com/jian-projects/agcl.