A Mutually Enhanced Bidirectional Approach for Jointly Mining User Demand and Sentiment (Student Abstract)

Authors

  • Xue Mao Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China
  • Haoda Qian Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China
  • Minjie Yuan Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China
  • Qiudan Li Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China

DOI:

https://doi.org/10.1609/aaai.v37i13.26999

Keywords:

Natural Language Processing, Aspect-based Sentiment Analysis, User Demand Mining

Abstract

User demand mining aims to identify the implicit demand from the e-commerce reviews, which are always irregular, vague and diverse. Existing sentiment analysis research mainly focuses on aspect-opinion-sentiment triplet extraction, while the deeper user demands remain unexplored. In this paper, we formulate a novel research question of jointly mining aspect-opinion-sentiment-demand, and propose a Mutually Enhanced Bidirectional Extraction (MEMB) framework for capturing the dynamic interaction among different types of information. Finally, experiments on Chinese e-commerce data demonstrate the efficacy of the proposed model.

Downloads

Published

2024-07-15

How to Cite

Mao, X., Qian, H., Yuan, M., & Li, Q. (2024). A Mutually Enhanced Bidirectional Approach for Jointly Mining User Demand and Sentiment (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 16278-16279. https://doi.org/10.1609/aaai.v37i13.26999