Multi-granular document-level sentiment topic analysis for online reviews

Author(s):  
Faliang Huang ◽  
Changan Yuan ◽  
Yingzhou Bi ◽  
Jianbo Lu ◽  
Liqiong Lu ◽  
...  
2018 ◽  
Vol 55 (2) ◽  
pp. 163-177 ◽  
Author(s):  
Yang Wang ◽  
Alexander Chaudhry

In this study, the authors investigate the externalities of managers' responses (MRs) to online reviews on popular travel websites. Specifically, the authors examine the effect of publicly responding to hotel guests' reviews on subsequent reviewer ratings. The authors find that manager responses to negative reviews (MR-N) can significantly influence subsequent opinion in a positive way if those responses are observable at the time of reviewing. Notably, the findings show this externality to be negative for manager responses to positive reviews (MR-P). The authors conduct a topic analysis on review texts and corresponding MRs to study the moderating role of response tailoring on the opinion externalities of MR. The authors show that tailored MR amplifies the positive (negative) impact of MR-N (MR-P) on subsequent opinion. Intuitively, tailoring an MR-N adds specificity to the hotel's complaint management strategy, bolstering the positive effects of MR-N on subsequent opinion. However, by highlighting specific positive elements of a review, managers' intent for responding is brought into question as they take advantage of reviewers' positive feedback to promote their hotel.


Author(s):  
Dr. Akey Sungheetha ◽  
Dr. Rajesh Sharma R,

Aspect-level sentiment classification is the aspect of determining the text in a given document and classifying it according to the sentiment polarity with respect to the objective. However, since annotation cost is very high, it might serve a big obstacle for this purpose. However, from a consumer point of view, this is highly effective in reading document-level labelled data such as reviews which are present online using neural network. The online reviews are packed with sentiment encoded text which can be analyzed using this proposed methodology. In this paper a Transfer Capsule Network model is used which has the ability to transfer the knowledge gained at document-level to the aspect-level to classify according to the sentiment detected in the text. As the first step, the sentence is broken down in semantic representations using aspect routing to form semantic capsule data of both document-level and aspect-level. This routing approach is extended to group the semantic capsules for transfer learning framework. The effectiveness of the proposed methodology are experimented and demonstrated to determine how superior they are to the other methodologies proposed.


2019 ◽  
Vol 56 (2) ◽  
pp. 172-184 ◽  
Author(s):  
Xiaolin Li ◽  
Chaojiang Wu ◽  
Feng Mai

2018 ◽  
Vol 2018 ◽  
pp. 200-200
Author(s):  
Kok Wei Khong ◽  
◽  
Fon Sim Ong ◽  
Babajide AbuBakr Muritala ◽  
Ken Kyid Yeoh

Sign in / Sign up

Export Citation Format

Share Document