Improving Recommendation Accuracy by Considering Electronic Word-of-Mouth and the Effects of Its Propagation Using Collective Matrix Factorization

Ren Shiou Liu, Tian Chih Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

In recent years, recommender systems have become an important tool for increasing sales and revenues for many online retailers, such as Amazon and eBay. Many of these recommender systems predict a user's interest in the items or the products by using the browsing/shopping history or item rating records of the user. However, many research studies show that, before making a purchase, people often read on-line reviews and exchange their opinion with friends in their social circles. The resulting electronic word-of-mouth (eWOM) has huge impact on customer's final purchase or decision. Nonetheless, most of the recommender systems in the current literature do not consider eWOM, let alone the effect of its propagation. Therefore, we propose a new recommendation model based on the collective matrix factorization technique for predicting customer's preferences in this paper. Our model not only considers customers' personal taste, their trust relationships, but also the effect of eWOM propagation in their social networks. We conduct a series of experiments using real-life data crawled from Epinions and Amazon. Experimental results show that our model significantly outperforms other closely related models that do not consider eWOM propagation effects by 5%-13% in terms of both RMSE and MAE.

Original languageEnglish
Title of host publicationProceedings - 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing, DASC 2016, 2016 IEEE 14th International Conference on Pervasive Intelligence and Computing, PICom 2016, 2016 IEEE 2nd International Conference on Big Data Intelligence and Computing, DataCom 2016 and 2016 IEEE Cyber Science and Technology Congress, CyberSciTech 2016, DASC-PICom-DataCom-CyberSciTech 2016
EditorsKevin I-Kai Wang, Qun Jin, Md Zakirul Alam Bhuiyan, Qingchen Zhang, Ching-Hsien Hsu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages696-703
Number of pages8
ISBN (Electronic)9781509040650
DOIs
Publication statusPublished - 2016 Oct 11
Event14th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2016, 14th IEEE International Conference on Pervasive Intelligence and Computing, PICom 2016, 2nd IEEE International Conference on Big Data Intelligence and Computing, DataCom 2016 and 2016 IEEE Cyber Science and Technology Congress, CyberSciTech 2016, DASC-PICom-DataCom-CyberSciTech 2016 - Auckland, New Zealand
Duration: 2016 Aug 82016 Aug 10

Publication series

NameProceedings - 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing, DASC 2016, 2016 IEEE 14th International Conference on Pervasive Intelligence and Computing, PICom 2016, 2016 IEEE 2nd International Conference on Big Data Intelligence and Computing, DataCom 2016 and 2016 IEEE Cyber Science and Technology Congress, CyberSciTech 2016, DASC-PICom-DataCom-CyberSciTech 2016

Other

Other14th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2016, 14th IEEE International Conference on Pervasive Intelligence and Computing, PICom 2016, 2nd IEEE International Conference on Big Data Intelligence and Computing, DataCom 2016 and 2016 IEEE Cyber Science and Technology Congress, CyberSciTech 2016, DASC-PICom-DataCom-CyberSciTech 2016
CountryNew Zealand
CityAuckland
Period16-08-0816-08-10

Fingerprint

Factorization
Recommender systems
Sales
History
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Information Systems
  • Computer Science (miscellaneous)
  • Artificial Intelligence
  • Computer Networks and Communications

Cite this

Liu, R. S., & Yang, T. C. (2016). Improving Recommendation Accuracy by Considering Electronic Word-of-Mouth and the Effects of Its Propagation Using Collective Matrix Factorization. In K. I-K. Wang, Q. Jin, M. Z. A. Bhuiyan, Q. Zhang, & C-H. Hsu (Eds.), Proceedings - 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing, DASC 2016, 2016 IEEE 14th International Conference on Pervasive Intelligence and Computing, PICom 2016, 2016 IEEE 2nd International Conference on Big Data Intelligence and Computing, DataCom 2016 and 2016 IEEE Cyber Science and Technology Congress, CyberSciTech 2016, DASC-PICom-DataCom-CyberSciTech 2016 (pp. 696-703). [7588922] (Proceedings - 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing, DASC 2016, 2016 IEEE 14th International Conference on Pervasive Intelligence and Computing, PICom 2016, 2016 IEEE 2nd International Conference on Big Data Intelligence and Computing, DataCom 2016 and 2016 IEEE Cyber Science and Technology Congress, CyberSciTech 2016, DASC-PICom-DataCom-CyberSciTech 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DASC-PICom-DataCom-CyberSciTec.2016.124
Liu, Ren Shiou ; Yang, Tian Chih. / Improving Recommendation Accuracy by Considering Electronic Word-of-Mouth and the Effects of Its Propagation Using Collective Matrix Factorization. Proceedings - 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing, DASC 2016, 2016 IEEE 14th International Conference on Pervasive Intelligence and Computing, PICom 2016, 2016 IEEE 2nd International Conference on Big Data Intelligence and Computing, DataCom 2016 and 2016 IEEE Cyber Science and Technology Congress, CyberSciTech 2016, DASC-PICom-DataCom-CyberSciTech 2016. editor / Kevin I-Kai Wang ; Qun Jin ; Md Zakirul Alam Bhuiyan ; Qingchen Zhang ; Ching-Hsien Hsu. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 696-703 (Proceedings - 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing, DASC 2016, 2016 IEEE 14th International Conference on Pervasive Intelligence and Computing, PICom 2016, 2016 IEEE 2nd International Conference on Big Data Intelligence and Computing, DataCom 2016 and 2016 IEEE Cyber Science and Technology Congress, CyberSciTech 2016, DASC-PICom-DataCom-CyberSciTech 2016).
@inproceedings{3480cf71444f4acba5eaa6c1aa2f6812,
title = "Improving Recommendation Accuracy by Considering Electronic Word-of-Mouth and the Effects of Its Propagation Using Collective Matrix Factorization",
abstract = "In recent years, recommender systems have become an important tool for increasing sales and revenues for many online retailers, such as Amazon and eBay. Many of these recommender systems predict a user's interest in the items or the products by using the browsing/shopping history or item rating records of the user. However, many research studies show that, before making a purchase, people often read on-line reviews and exchange their opinion with friends in their social circles. The resulting electronic word-of-mouth (eWOM) has huge impact on customer's final purchase or decision. Nonetheless, most of the recommender systems in the current literature do not consider eWOM, let alone the effect of its propagation. Therefore, we propose a new recommendation model based on the collective matrix factorization technique for predicting customer's preferences in this paper. Our model not only considers customers' personal taste, their trust relationships, but also the effect of eWOM propagation in their social networks. We conduct a series of experiments using real-life data crawled from Epinions and Amazon. Experimental results show that our model significantly outperforms other closely related models that do not consider eWOM propagation effects by 5{\%}-13{\%} in terms of both RMSE and MAE.",
author = "Liu, {Ren Shiou} and Yang, {Tian Chih}",
year = "2016",
month = "10",
day = "11",
doi = "10.1109/DASC-PICom-DataCom-CyberSciTec.2016.124",
language = "English",
series = "Proceedings - 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing, DASC 2016, 2016 IEEE 14th International Conference on Pervasive Intelligence and Computing, PICom 2016, 2016 IEEE 2nd International Conference on Big Data Intelligence and Computing, DataCom 2016 and 2016 IEEE Cyber Science and Technology Congress, CyberSciTech 2016, DASC-PICom-DataCom-CyberSciTech 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "696--703",
editor = "Wang, {Kevin I-Kai} and Qun Jin and Bhuiyan, {Md Zakirul Alam} and Qingchen Zhang and Ching-Hsien Hsu",
booktitle = "Proceedings - 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing, DASC 2016, 2016 IEEE 14th International Conference on Pervasive Intelligence and Computing, PICom 2016, 2016 IEEE 2nd International Conference on Big Data Intelligence and Computing, DataCom 2016 and 2016 IEEE Cyber Science and Technology Congress, CyberSciTech 2016, DASC-PICom-DataCom-CyberSciTech 2016",
address = "United States",

}

Liu, RS & Yang, TC 2016, Improving Recommendation Accuracy by Considering Electronic Word-of-Mouth and the Effects of Its Propagation Using Collective Matrix Factorization. in KI-K Wang, Q Jin, MZA Bhuiyan, Q Zhang & C-H Hsu (eds), Proceedings - 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing, DASC 2016, 2016 IEEE 14th International Conference on Pervasive Intelligence and Computing, PICom 2016, 2016 IEEE 2nd International Conference on Big Data Intelligence and Computing, DataCom 2016 and 2016 IEEE Cyber Science and Technology Congress, CyberSciTech 2016, DASC-PICom-DataCom-CyberSciTech 2016., 7588922, Proceedings - 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing, DASC 2016, 2016 IEEE 14th International Conference on Pervasive Intelligence and Computing, PICom 2016, 2016 IEEE 2nd International Conference on Big Data Intelligence and Computing, DataCom 2016 and 2016 IEEE Cyber Science and Technology Congress, CyberSciTech 2016, DASC-PICom-DataCom-CyberSciTech 2016, Institute of Electrical and Electronics Engineers Inc., pp. 696-703, 14th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2016, 14th IEEE International Conference on Pervasive Intelligence and Computing, PICom 2016, 2nd IEEE International Conference on Big Data Intelligence and Computing, DataCom 2016 and 2016 IEEE Cyber Science and Technology Congress, CyberSciTech 2016, DASC-PICom-DataCom-CyberSciTech 2016, Auckland, New Zealand, 16-08-08. https://doi.org/10.1109/DASC-PICom-DataCom-CyberSciTec.2016.124

Improving Recommendation Accuracy by Considering Electronic Word-of-Mouth and the Effects of Its Propagation Using Collective Matrix Factorization. / Liu, Ren Shiou; Yang, Tian Chih.

Proceedings - 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing, DASC 2016, 2016 IEEE 14th International Conference on Pervasive Intelligence and Computing, PICom 2016, 2016 IEEE 2nd International Conference on Big Data Intelligence and Computing, DataCom 2016 and 2016 IEEE Cyber Science and Technology Congress, CyberSciTech 2016, DASC-PICom-DataCom-CyberSciTech 2016. ed. / Kevin I-Kai Wang; Qun Jin; Md Zakirul Alam Bhuiyan; Qingchen Zhang; Ching-Hsien Hsu. Institute of Electrical and Electronics Engineers Inc., 2016. p. 696-703 7588922 (Proceedings - 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing, DASC 2016, 2016 IEEE 14th International Conference on Pervasive Intelligence and Computing, PICom 2016, 2016 IEEE 2nd International Conference on Big Data Intelligence and Computing, DataCom 2016 and 2016 IEEE Cyber Science and Technology Congress, CyberSciTech 2016, DASC-PICom-DataCom-CyberSciTech 2016).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Improving Recommendation Accuracy by Considering Electronic Word-of-Mouth and the Effects of Its Propagation Using Collective Matrix Factorization

AU - Liu, Ren Shiou

AU - Yang, Tian Chih

PY - 2016/10/11

Y1 - 2016/10/11

N2 - In recent years, recommender systems have become an important tool for increasing sales and revenues for many online retailers, such as Amazon and eBay. Many of these recommender systems predict a user's interest in the items or the products by using the browsing/shopping history or item rating records of the user. However, many research studies show that, before making a purchase, people often read on-line reviews and exchange their opinion with friends in their social circles. The resulting electronic word-of-mouth (eWOM) has huge impact on customer's final purchase or decision. Nonetheless, most of the recommender systems in the current literature do not consider eWOM, let alone the effect of its propagation. Therefore, we propose a new recommendation model based on the collective matrix factorization technique for predicting customer's preferences in this paper. Our model not only considers customers' personal taste, their trust relationships, but also the effect of eWOM propagation in their social networks. We conduct a series of experiments using real-life data crawled from Epinions and Amazon. Experimental results show that our model significantly outperforms other closely related models that do not consider eWOM propagation effects by 5%-13% in terms of both RMSE and MAE.

AB - In recent years, recommender systems have become an important tool for increasing sales and revenues for many online retailers, such as Amazon and eBay. Many of these recommender systems predict a user's interest in the items or the products by using the browsing/shopping history or item rating records of the user. However, many research studies show that, before making a purchase, people often read on-line reviews and exchange their opinion with friends in their social circles. The resulting electronic word-of-mouth (eWOM) has huge impact on customer's final purchase or decision. Nonetheless, most of the recommender systems in the current literature do not consider eWOM, let alone the effect of its propagation. Therefore, we propose a new recommendation model based on the collective matrix factorization technique for predicting customer's preferences in this paper. Our model not only considers customers' personal taste, their trust relationships, but also the effect of eWOM propagation in their social networks. We conduct a series of experiments using real-life data crawled from Epinions and Amazon. Experimental results show that our model significantly outperforms other closely related models that do not consider eWOM propagation effects by 5%-13% in terms of both RMSE and MAE.

UR - http://www.scopus.com/inward/record.url?scp=84995467824&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84995467824&partnerID=8YFLogxK

U2 - 10.1109/DASC-PICom-DataCom-CyberSciTec.2016.124

DO - 10.1109/DASC-PICom-DataCom-CyberSciTec.2016.124

M3 - Conference contribution

AN - SCOPUS:84995467824

T3 - Proceedings - 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing, DASC 2016, 2016 IEEE 14th International Conference on Pervasive Intelligence and Computing, PICom 2016, 2016 IEEE 2nd International Conference on Big Data Intelligence and Computing, DataCom 2016 and 2016 IEEE Cyber Science and Technology Congress, CyberSciTech 2016, DASC-PICom-DataCom-CyberSciTech 2016

SP - 696

EP - 703

BT - Proceedings - 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing, DASC 2016, 2016 IEEE 14th International Conference on Pervasive Intelligence and Computing, PICom 2016, 2016 IEEE 2nd International Conference on Big Data Intelligence and Computing, DataCom 2016 and 2016 IEEE Cyber Science and Technology Congress, CyberSciTech 2016, DASC-PICom-DataCom-CyberSciTech 2016

A2 - Wang, Kevin I-Kai

A2 - Jin, Qun

A2 - Bhuiyan, Md Zakirul Alam

A2 - Zhang, Qingchen

A2 - Hsu, Ching-Hsien

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Liu RS, Yang TC. Improving Recommendation Accuracy by Considering Electronic Word-of-Mouth and the Effects of Its Propagation Using Collective Matrix Factorization. In Wang KI-K, Jin Q, Bhuiyan MZA, Zhang Q, Hsu C-H, editors, Proceedings - 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing, DASC 2016, 2016 IEEE 14th International Conference on Pervasive Intelligence and Computing, PICom 2016, 2016 IEEE 2nd International Conference on Big Data Intelligence and Computing, DataCom 2016 and 2016 IEEE Cyber Science and Technology Congress, CyberSciTech 2016, DASC-PICom-DataCom-CyberSciTech 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 696-703. 7588922. (Proceedings - 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing, DASC 2016, 2016 IEEE 14th International Conference on Pervasive Intelligence and Computing, PICom 2016, 2016 IEEE 2nd International Conference on Big Data Intelligence and Computing, DataCom 2016 and 2016 IEEE Cyber Science and Technology Congress, CyberSciTech 2016, DASC-PICom-DataCom-CyberSciTech 2016). https://doi.org/10.1109/DASC-PICom-DataCom-CyberSciTec.2016.124