Recommend for a Reason: Unlocking the Power of Unsupervised Aspect-Sentiment Co-Extraction

Zeyu Li, Wei Cheng, Reema Kshetramade, John Houser, Haifeng Chen, Wei Wang


Abstract
Compliments and concerns in reviews are valuable for understanding users’ shopping interests and their opinions with respect to specific aspects of certain items. Existing review-based recommenders favor large and complex language encoders that can only learn latent and uninterpretable text representations. They lack explicit user-attention and item-property modeling, which however could provide valuable information beyond the ability to recommend items. Therefore, we propose a tightly coupled two-stage approach, including an Aspect-Sentiment Pair Extractor (ASPE) and an Attention-Property-aware Rating Estimator (APRE). Unsupervised ASPE mines Aspect-Sentiment pairs (AS-pairs) and APRE predicts ratings using AS-pairs as concrete aspect-level evidences. Extensive experiments on seven real-world Amazon Review Datasets demonstrate that ASPE can effectively extract AS-pairs which enable APRE to deliver superior accuracy over the leading baselines.
Anthology ID:
2021.findings-emnlp.66
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
763–778
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.66
DOI:
10.18653/v1/2021.findings-emnlp.66
Bibkey:
Cite (ACL):
Zeyu Li, Wei Cheng, Reema Kshetramade, John Houser, Haifeng Chen, and Wei Wang. 2021. Recommend for a Reason: Unlocking the Power of Unsupervised Aspect-Sentiment Co-Extraction. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 763–778, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Recommend for a Reason: Unlocking the Power of Unsupervised Aspect-Sentiment Co-Extraction (Li et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.66.pdf
Video:
 https://aclanthology.org/2021.findings-emnlp.66.mp4
Code
 zyli93/aspe-apre