Affiliation:
1. Xinjiang Multilingual Information Technology Laboratory, Xinjiang Multilingual Information Technology Research Center, College of Information Science and Engineering, Xinjiang University, Urumqi 830017, China
Abstract
In sentiment analysis, biased user reviews can have a detrimental impact on a company’s evaluation. Therefore, identifying such users can be highly beneficial as their reviews are not based on reality but on their characteristics rooted in their psychology. Furthermore, biased users may be seen as instigators of other prejudiced information on social media. Thus, proposing a method to help detect polarized opinions in product reviews would offer significant advantages. This paper proposes a new method for sentiment classification of multimodal data, which is called UsbVisdaNet (User Behavior Visual Distillation and Attention Network). The method aims to identify biased user reviews by analyzing their psychological behaviors. It can identify both positive and negative users and improves sentiment classification results that may be skewed due to subjective biases in user opinions by leveraging user behavior information. Through ablation and comparison experiments, the effectiveness of UsbVisdaNet is demonstrated, achieving superior sentiment classification performance on the Yelp multimodal dataset. Our research pioneers the integration of user behavior features, text features, and image features at multiple hierarchical levels within this domain.
Funder
Natural Science Foundation of Autonomous Region
Autonomous Region High-Level Innovative Talent Project
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference38 articles.
1. Calabrese, B., and Cannataro, M. (2015, January 6–10). Sentiment analysis and affective computing: Methods and applications. Proceedings of the Brain-Inspired Computing: Second International Workshop, BrainComp 2015, Cetraro, Italy. Revised Selected Papers 2.
2. Affective computing;Lisetti;Pattern Anal. Appl.,1998
3. Cross-modal image sentiment analysis via deep correlation of textual semantic;Zhang;Knowl.-Based Syst.,2021
4. Various syncretic co-attention network for multimodal sentiment analysis;Cao;Concurr. Comput. Pract. Exp.,2020
5. Social image sentiment analysis by exploiting multimodal content and heterogeneous relations;Xu;IEEE Trans. Ind. Inform.,2020
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献