Journal
KYBERNETES
Volume 48, Issue 5, Pages 990-1010Publisher
EMERALD GROUP PUBLISHING LTD
DOI: 10.1108/K-01-2018-0029
Keywords
Sentiment analysis; Intuitionistic fuzzy set; Multiple attribute decision-making; Product ranking; Sentiment word framework
Categories
Ask authors/readers for more resources
Purpose The purpose of this paper is to rank products by combining sentiment analysis (SA) and multiple attribute decision-making (MADM). Design/methodology/approach This research constructs intuitionistic fuzzy (IF)-based sentiment word framework and corresponding computation rules, which aim to calculate the sentiment score of each sentiment phase. Based on intuitionistic fuzzy weighted averaging operator, the authors aggregate the overall performance of each feature for different products. Then, the MADM method can be used, TODIM (an acronym in Portuguese of interactive and multi-criteria decision making) in this paper, to rank product through online reviews. Findings The results of the research show the superiority and applicability of proposed method in ranking products with online reviews. Originality/value This paper proposes IF-based sentiment word framework and corresponding computation rules, which is a novel idea to express both the sentiment orientations (positive, negative and neutral) and emotional intensities. In addition, this research makes full use of knowledge from both experts and online reviewers. Further, attention degree of each feature is considered in the process of calculating weight of different features, which is rarely seen in current studies. This paper makes full use of SA, fuzzy control theory and MADM theory to handle vague information (online comments) and rank alternative products, which can promote future perspectives and developments.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available