TY - GEN
T1 - Reliability Evaluation Based on Sentiment Analysis of Online Comment
AU - Zhang, Xinyu
AU - Xie, Guanxu
AU - Li, Daqing
AU - Kang, Rui
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/7/2
Y1 - 2018/7/2
N2 - E-commerce products are becoming widely acceptable because of their advantages in terms of purchasing convenience. At the same time, due to the unique characteristics of e-commerce products, it is increasingly difficult for customers to define and evaluate the authenticity and reliability of products, which usually requires a large amount of failure data through the reliability test that is non-applicable to e-commerce products. Here we provide a novel reliability analysis based on users' subjective sentiments for e-commerce products. Based on data from online sellers and user comments, we calculate the reliability of e-commerce products by a neural network for their sentimental values. We evaluate and weight the usefulness of each comment by using multifaceted data such as comment date, buyer's credit level, and the number of comments in a given day. Our findings are helpful for evaluating the reliability of e-commerce products, thus better design potential new products with large user adoption.
AB - E-commerce products are becoming widely acceptable because of their advantages in terms of purchasing convenience. At the same time, due to the unique characteristics of e-commerce products, it is increasingly difficult for customers to define and evaluate the authenticity and reliability of products, which usually requires a large amount of failure data through the reliability test that is non-applicable to e-commerce products. Here we provide a novel reliability analysis based on users' subjective sentiments for e-commerce products. Based on data from online sellers and user comments, we calculate the reliability of e-commerce products by a neural network for their sentimental values. We evaluate and weight the usefulness of each comment by using multifaceted data such as comment date, buyer's credit level, and the number of comments in a given day. Our findings are helpful for evaluating the reliability of e-commerce products, thus better design potential new products with large user adoption.
KW - e-commerce products
KW - neural network
KW - sentimental analysis
KW - subjective reliability
UR - https://www.scopus.com/pages/publications/85067041883
U2 - 10.1109/ICRMS.2018.00026
DO - 10.1109/ICRMS.2018.00026
M3 - 会议稿件
AN - SCOPUS:85067041883
T3 - Proceedings - 12th International Conference on Reliability, Maintainability, and Safety, ICRMS 2018
SP - 88
EP - 91
BT - Proceedings - 12th International Conference on Reliability, Maintainability, and Safety, ICRMS 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 12th International Conference on Reliability, Maintainability, and Safety, ICRMS 2018
Y2 - 17 October 2018 through 19 October 2018
ER -