User review helpfulness assessment based on sentiment analysis
| Published date | 13 February 2020 |
| DOI | https://doi.org/10.1108/EL-08-2019-0200 |
| Pages | 337-351 |
| Date | 13 February 2020 |
| Author | Ziming Zeng,Zhi Zhou,Xiangming Mu |
| Subject Matter | Information & knowledge management,Information & communications technology,Internet |
User review helpfulness
assessment based on
sentiment analysis
Ziming Zeng and Zhi Zhou
Center for Studies of Information Resources,WuhanUniversity,Wuhan,China,and
Xiangming Mu
School of Information Studies, University of Wisconsin-Milwaukee,
Milwaukee, Wisconsin, USA
Abstract
Purpose –This paper aims to investigate the relationship between sentiment and review helpfulness and
develop a method to fully use sentiment features in review helpfulness assessment. In addition, this paper
exploreswhether product type influences evaluating review helpfulness.
Design/methodology/approach –First, a high-quality data set with a manually coded helpfulness
score was constructed. Second, detailed research question methods were conducted. Finally, methods were
applied to thedata set to extract information gain and sentimentscores. Gradient boosting and random forest
methods were used to classify the data set with these features through recall, precision and F-measure to
understandthe research questions.
Findings –Review sentiment has a deep relationship with review helpfulness, and it can be a strong
predictor of reviewhelpfulness by refining it into more detailed scores; a combinationof sentiment scores and
information gain works very well on classification for two product types. Product type does not show a
significantinfluence on helpfulness assessment.
Originality/value –This paper provides a different perspective for measuring review sentiment by
clarifying the relationship between sentiment and review helpfulness, analysing the role of product type in
review helpfulness assessment, and proposing a high-value feature combination. In addition, the author
believesthat the assessment method can be effectively applied to practical works.
Keywords Sentiment analysis, User reviews, Experience products, Helpfulness assessment,
Search products
Paper type Research paper
Introduction
User reviews play an importantrole in the electronics marketplace, and each usercan share
their opinions and ideas about goods and purchaseexperiences on website platforms; these
comments can help potential consumers make buying decisions (Filieri, 2015). Thus, many
practical works have attempted to develop review systems to show these reviews; for
example, Amazon.com places “top positive reviews”and “top critical reviews”to help
customers make a comprehensive decision. The importance of user reviews has also
inspired researchersto find ways to use this resource better.
This research was supported by: National Natural Science Foundation of China (Grant # 71673203);
World First Class Subject Foundation of Ministry of Education of China [Library, Information and
Data Science]; Key Research Institutes of Philosophy and Social Science by Ministry of Education, PR
China (Grant # 16JJD870003); and the China Scholarship Council (Grant # 201806270049).
Sentiment
analysis
337
Received30 August 2019
Revised7 November 2019
28December 2019
Accepted11 January 2020
TheElectronic Library
Vol.38 No. 2, 2020
pp. 337-351
© Emerald Publishing Limited
0264-0473
DOI 10.1108/EL-08-2019-0200
The current issue and full text archive of this journal is available on Emerald Insight at:
https://www.emerald.com/insight/0264-0473.htm
To continue reading
Request your trial