AX-MABSA: A Framework for Extremely Weakly Supervised Multi-label Aspect Based Sentiment Analysis

Sabyasachi Kamila, Walid Magdy, Sourav Dutta, MingXue Wang


Abstract
Aspect Based Sentiment Analysis is a dominant research area with potential applications in social media analytics, business, finance, and health. Prior works in this area are primarily based on supervised methods, with a few techniques using weak supervision limited to predicting a single aspect category per review sentence. In this paper, we present an extremely weakly supervised multi-label Aspect Category Sentiment Analysis framework which does not use any labelled data. We only rely on a single word per class as an initial indicative information. We further propose an automatic word selection technique to choose these seed categories and sentiment words. We explore unsupervised language model post-training to improve the overall performance, and propose a multi-label generator model to generate multiple aspect category-sentiment pairs per review sentence. Experiments conducted on four benchmark datasets showcase our method to outperform other weakly supervised baselines by a significant margin.
Anthology ID:
2022.emnlp-main.412
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6136–6147
Language:
URL:
https://aclanthology.org/2022.emnlp-main.412
DOI:
10.18653/v1/2022.emnlp-main.412
Bibkey:
Cite (ACL):
Sabyasachi Kamila, Walid Magdy, Sourav Dutta, and MingXue Wang. 2022. AX-MABSA: A Framework for Extremely Weakly Supervised Multi-label Aspect Based Sentiment Analysis. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 6136–6147, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
AX-MABSA: A Framework for Extremely Weakly Supervised Multi-label Aspect Based Sentiment Analysis (Kamila et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.412.pdf