What Makes an Online Review More Helpful: An Interpretation Framework Using XGBoost and SHAP Values
Online product reviews play important roles in the word-of-mouth marketing of e-commerce enterprises, but only helpful reviews actually influence customers’ purchase decisions. Current research focuses on how to predict the helpfulness of a review but lacks a thorough analysis of why it is helpful....
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-11-01
|
| Series: | Journal of Theoretical and Applied Electronic Commerce Research |
| Subjects: | |
| Online Access: | https://www.mdpi.com/0718-1876/16/3/29 |
| _version_ | 1797520772419289088 |
|---|---|
| author | Yuan Meng Nianhua Yang Zhilin Qian Gaoyu Zhang |
| author_facet | Yuan Meng Nianhua Yang Zhilin Qian Gaoyu Zhang |
| author_sort | Yuan Meng |
| collection | DOAJ |
| description | Online product reviews play important roles in the word-of-mouth marketing of e-commerce enterprises, but only helpful reviews actually influence customers’ purchase decisions. Current research focuses on how to predict the helpfulness of a review but lacks a thorough analysis of why it is helpful. In this paper, feature sets covering review text and context cues are firstly proposed to represent review helpfulness. Then, a set of gradient boosted trees (GBT) models is introduced, and the optimal one, which as implemented in eXtreme Gradient Boosting (XGBoost), is chosen to predict and explain review helpfulness. Specially, by including the SHAP (Shapley) values method to quantify feature contribution, this paper presents an integrated framework to better interpret why a review is helpful at both the macro and micro levels. Based on real data from Amazon.cn, this paper reveals that the number of words contributes the most to the helpfulness of reviews on headsets and is interactively influenced by features like the number of sentences or feature frequency, while feature frequency contributes the most to the helpfulness of facial cleanser reviews and is interactively influenced by the number of adjectives used in the review or the review’s entropy. Both datasets show that individual feature contributions vary from review to review, and individual joint contributions gradually decrease with the increase of feature values. |
| first_indexed | 2024-03-10T08:01:21Z |
| format | Article |
| id | doaj.art-c499f794f1d54231bc55537f800230ea |
| institution | Directory Open Access Journal |
| issn | 0718-1876 |
| language | English |
| last_indexed | 2024-03-10T08:01:21Z |
| publishDate | 2020-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Theoretical and Applied Electronic Commerce Research |
| spelling | doaj.art-c499f794f1d54231bc55537f800230ea2023-11-22T11:28:44ZengMDPI AGJournal of Theoretical and Applied Electronic Commerce Research0718-18762020-11-0116346649010.3390/jtaer16030029What Makes an Online Review More Helpful: An Interpretation Framework Using XGBoost and SHAP ValuesYuan Meng0Nianhua Yang1Zhilin Qian2Gaoyu Zhang3School of Statistics and Information, Shanghai University of International Business and Economics, Shanghai 201620, ChinaSchool of Statistics and Information, Shanghai University of International Business and Economics, Shanghai 201620, ChinaSchool of Statistics and Information, Shanghai University of International Business and Economics, Shanghai 201620, ChinaSchool of Information Management, Shanghai Lixin University of Accounting and Finance, Shanghai 201209, ChinaOnline product reviews play important roles in the word-of-mouth marketing of e-commerce enterprises, but only helpful reviews actually influence customers’ purchase decisions. Current research focuses on how to predict the helpfulness of a review but lacks a thorough analysis of why it is helpful. In this paper, feature sets covering review text and context cues are firstly proposed to represent review helpfulness. Then, a set of gradient boosted trees (GBT) models is introduced, and the optimal one, which as implemented in eXtreme Gradient Boosting (XGBoost), is chosen to predict and explain review helpfulness. Specially, by including the SHAP (Shapley) values method to quantify feature contribution, this paper presents an integrated framework to better interpret why a review is helpful at both the macro and micro levels. Based on real data from Amazon.cn, this paper reveals that the number of words contributes the most to the helpfulness of reviews on headsets and is interactively influenced by features like the number of sentences or feature frequency, while feature frequency contributes the most to the helpfulness of facial cleanser reviews and is interactively influenced by the number of adjectives used in the review or the review’s entropy. Both datasets show that individual feature contributions vary from review to review, and individual joint contributions gradually decrease with the increase of feature values.https://www.mdpi.com/0718-1876/16/3/29online reviewreview helpfulnessSHAP valuesXGBoostfeature contributionjoint feature contribution |
| spellingShingle | Yuan Meng Nianhua Yang Zhilin Qian Gaoyu Zhang What Makes an Online Review More Helpful: An Interpretation Framework Using XGBoost and SHAP Values Journal of Theoretical and Applied Electronic Commerce Research online review review helpfulness SHAP values XGBoost feature contribution joint feature contribution |
| title | What Makes an Online Review More Helpful: An Interpretation Framework Using XGBoost and SHAP Values |
| title_full | What Makes an Online Review More Helpful: An Interpretation Framework Using XGBoost and SHAP Values |
| title_fullStr | What Makes an Online Review More Helpful: An Interpretation Framework Using XGBoost and SHAP Values |
| title_full_unstemmed | What Makes an Online Review More Helpful: An Interpretation Framework Using XGBoost and SHAP Values |
| title_short | What Makes an Online Review More Helpful: An Interpretation Framework Using XGBoost and SHAP Values |
| title_sort | what makes an online review more helpful an interpretation framework using xgboost and shap values |
| topic | online review review helpfulness SHAP values XGBoost feature contribution joint feature contribution |
| url | https://www.mdpi.com/0718-1876/16/3/29 |
| work_keys_str_mv | AT yuanmeng whatmakesanonlinereviewmorehelpfulaninterpretationframeworkusingxgboostandshapvalues AT nianhuayang whatmakesanonlinereviewmorehelpfulaninterpretationframeworkusingxgboostandshapvalues AT zhilinqian whatmakesanonlinereviewmorehelpfulaninterpretationframeworkusingxgboostandshapvalues AT gaoyuzhang whatmakesanonlinereviewmorehelpfulaninterpretationframeworkusingxgboostandshapvalues |