Computer Science ›› 2020, Vol. 47 ›› Issue (10): 69-74.doi: 10.11896/jsjkx.190700034

• Database & Big Data & Data Science • Previous Articles     Next Articles

Helpfulness Degree Prediction Model of Online Reviews Fusing Information Gain and Gradient Decline Algorithms

FENG Jin-zhan, CAI Shu-qin   

  1. School of Management,Huazhong University of Science and Technology,Wuhan 430074,China
  • Received:2019-07-03 Revised:2019-09-27 Online:2020-10-15 Published:2020-10-16
  • About author:FENG Jin-zhan,born in 1981,postgra-duate.His main research interests include business intelligence,management information and network complaint handling.
    CAI Shu-qin,born in 1955,Ph.D,professor,Ph.D supervisor.Her main research interests include business intelligence and management information system.
  • Supported by:
    National Natural Science Foundation of China (71371081) and Specialized Research Fund for the Doctoral Program of Higher Education (20130142110044)

Abstract: Because it is impossible to predict whether the text content of online product reviews is helpful for viewers,many reviewers write a large number of unhelpful reviews,which increases the cost of information search for potential consumers,and even reduces the possibility of potential consumers buying products.In order to improve the helpful online reviews rate of e-commerce platform and provide test function for reviewers,a prediction model of online reviews helpfulness is established.According to the text characteristics of online reviews,the model chooses three features of online reviews:the number of words,the helpful value of words,and the number of product features,to construct a model for predicting the helpfulness of online reviews.The helpful value is the information gain of words to distinguish the helpfulness of online reviews.And then,according to a large number of online reviews,by using the gradient descent algorithm,the model parameters are solved.The experimental results show that with the increase of the number of words,helpful value of words and the number of product features,the helpfulness of reviews increases continuously.The online reviews are divided into three levels:general,helpful and very helpful.The general predicted accuracy of online reviews is 92.96%,helpful accuracy is 94.83%,and very helpful accuracy is 67.63%.The average accuracy,recall and F1 of the model are 85.05%,82.81% and 83.72%,respectively.The results verify the feasibility of the model to predict the helpfulness of online reviews.

Key words: Gradient descent algorithm, Helpfulness degree, Information gain, Online reviews

CLC Number: 

  • TP391
[1]MIN H J,PARK J C.Identifying helpful reviews based on customers mentions about experiences[J].Expert Systems with Applications,2012,39(15):11830-11838.
[2]SHAN Y.How credible are online product reviews? The effects of self-generated and system-generated cues on source credibility evaluation[J].Computers in Human Behavior,2016,55:633-641.
[3]PENG L,ZHOU Q H,QIU J T.Research on the Model ofHelpfulness Factors of OnlineCustomer Reviews[J].Computer Science,2011,38(8):205-207.
[4]PAN Y,ZHANG J Q.Born Unequal:A Study of the Helpfulness of User-Generated Product Reviews[J].Journal of Retailing,2011,87(4):598-612.
[5]FILIERI R.What makes an online consumer review trustwor-thy?[J].Annals of Tourism Research,2016,58:46-64.
[6]HOMER P M.Message Framing and the Interrelationshipsamong Ad-Based Feelings,Affect,and Cognition[J].Journal of Advertising,1992,21(1):19-33.
[7]WU T Y,LIN C A.Predicting the effects of eWOM and online brand messaging:Source trust,bandwagon effect and innovation adoption factors[J].Telematics & Informatics,2017,34(2):470-480.
[8]WANG H W,MENG Y.Helpful Features Identification of Online Reviews Quality on GBDT Feature Contribution[J].Journal of Chinese Information Processing,2017,31(3):109-117.
[9]LI C,XIANG J,XIANG J.Assessment method of credibility on online product reviews[J].Journal of Computer Applications,2019,39(1):187-191.
[10]HU X G,CHEN F X,ZHANG Y H.Research on impact factors of online reviews’helpfulness based on product reviews data[J].Application Research of Computers,2016,33(12):3559-3561.
[11]SINGH J P,IRANI S,RANA N P,et al.Predicting the “helpfulness” of online consumer reviews[J].Journal of Business Research,2017,70(1):346-355.
[12]LEE S,CHOEH J Y.Predicting the helpfulness of onlinereviews using multilayer perceptron neural networks[J].Expert Systems with Applications,2014,41(6):3041-3046.
[13]SINGH J P,IRANI S,RANA N P,et al.Predicting the “helpfulness” of online consumer reviews[J].Journal of Business Research,2017,70:346-355.
[14]PARK Y J.Predicting the Helpfulness of Online Customer Reviews across Different Product Types[J].Sustainability,2018,10(6):1735.
[15]KRISHNAMOORTHY S.Linguistic features for review helpfulness prediction[J].Expert Systems with Applications,2015,42(7):3751-3759.
[16]JIANG W,ZHANG L,DAI Y,et al.Analyzing Helpfulness of Online Reviews for User Requirements Elictation[J].Chinese Journal of Computers,2013,36(1):119-131.
[17]QIU J P.Information Metrology (5) Lecture 5:The Law of Frequency Distribution of DocumentInformation Words-Zipf's Law[J].Information Studies:Theory& Application,2000(5):77-81.
[18]ZHANG Y H,LI Z W,ZHAO J C.How the Information Quality Affects the Online Review Usefulness?-An Emprical Analysis Based on Taobao Reciew Data[J].Chinese Journal of Management,2017,14(1):77-85.
[19]WANG Z H,JIANG W.Online Reviews Sentiment AnalysisModel Based on Rough Sets[J].Computer Engineering,2012,38(16):1-4.
[20]YU M Z,NARISA Z.Feature extraction method based on mutual self-expanding mode[J].Application Research of Computers,2017,34(4):977-980.
[21]XU Q,ZHANG X,YU S H,et al.Multi-feature-based classification method using random forest and superpixels for polarimetric SAR images[J].Journal of Remote Sensing,2019,23(4):685-694.
[1] ZHAO Zhi-qiang, YI Xiu-shuang, LI Jie, WANG Xing-wei. Research on DoS Intrusion Detection Technology of IPv6 Network Based on GR-AD-KNN Algorithm [J]. Computer Science, 2021, 48(6A): 524-528.
[2] YANG Feng. Symbolic Value Partition Algorithm Using Granular Computing [J]. Computer Science, 2018, 45(11A): 445-452.
[3] LI Hong-li, MENG Zu-qiang. Attribute Reduction Algorithm Using Information Gain and Inconsistency to Fill [J]. Computer Science, 2018, 45(10): 217-224.
[4] JIANG Fang, LI Guo-he and YUE Xiang. Semantic-based Feature Extraction Method for Document [J]. Computer Science, 2016, 43(2): 254-258.
[5] LI Ling, LIU Hua-wen, XU Xiao-dan and ZHAO Jian-min. Multi-label Feature Selection Algorithm Based on Information Gain [J]. Computer Science, 2015, 42(7): 52-56.
[6] LUO Hui,GUO Bin,YU Zhi-wen,WANG Zhu and FENG Yun. Friendship Prediction Based on Fusion of Network Topology and Geographical Features [J]. Computer Science, 2014, 41(6): 43-47.
[7] ZHAI Jun-chang,QIN Yu-ping and CHE Wei-wei. Improvement of Information Gain in Spam Filtering [J]. Computer Science, 2014, 41(6): 214-216.
[8] TANG Lei,LI Chun-ping and YANG Liu. Statistically Significant Sequential Pattern Mining Applying to Software Defect Prediction [J]. Computer Science, 2013, 40(5): 164-167.
[9] REN Yong-gong,YANG Xue,YANG Rong-jie and HU Zhi-dong. Text Feature Selection Methods Based on Information Gain and Feature Relation Tree [J]. Computer Science, 2013, 40(10): 252-256.
[10] . K-means Clustering Algorithm Based on Artificial Fish Swarm [J]. Computer Science, 2012, 39(12): 60-64.
[11] . Information-gain-based Text Feature Selection Method [J]. Computer Science, 2012, 39(11): 127-130.
[12] ZHANG Shu-bo, LAI Jian-huang. Cancer Relevant Genes Selection Approach from Integrated Information [J]. Computer Science, 2010, 37(12): 171-174.
[13] WU Kai-gui WAN Hong-bo ZHU Zheng-zhou (College of Computer, Chongqing University,Chongqing 400044,China). [J]. Computer Science, 2008, 35(5): 123-124.
[14] . [J]. Computer Science, 2007, 34(3): 181-185.
[15] REN Jiang-Tao, SUN Jing-Hao, HUANG Huan-Yu ,YIN Jian (Department of Computer Science, Zhongshan University, Guangzhou 510275). [J]. Computer Science, 2006, 33(10): 193-195.
Full text



No Suggested Reading articles found!