Developing a hybrid collaborative filtering recommendation system with opinion mining on purchase review

Youdong Yun, Danial Hooshyar, Jaechoon Jo, Heui Seok Lim

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

The most commonly used algorithm in recommendation systems is collaborative filtering. However, despite its wide use, the prediction accuracy of this algorithm is unexceptional. Furthermore, whether quantitative data such as product rating or purchase history reflect users’ actual taste is questionable. In this article, we propose a method to utilise user review data extracted with opinion mining for product recommendation systems. To evaluate the proposed method, we perform product recommendation test on Amazon product data, with and without the additional opinion mining result on Amazon purchase review data. The performances of these two variants are compared by means of precision, recall, true positive recommendation (TPR) and false positive recommendation (FPR). In this comparison, a large improvement in prediction accuracy was observed when the opinion mining data were taken into account. Based on these results, we answer two main questions: ‘Why is collaborative filtering algorithm not effective?’ and ‘Do quantitative data such as product rating or purchase history reflect users’ actual tastes?’

Original languageEnglish
JournalJournal of Information Science
DOIs
Publication statusAccepted/In press - 2017 Feb 1

Fingerprint

Collaborative filtering
Recommender systems
purchase
Data mining
product test
rating
history
performance

Keywords

  • Collaborative filtering
  • hybrid recommendation system
  • opinion mining
  • purchase review

ASJC Scopus subject areas

  • Information Systems
  • Library and Information Sciences

Cite this

Developing a hybrid collaborative filtering recommendation system with opinion mining on purchase review. / Yun, Youdong; Hooshyar, Danial; Jo, Jaechoon; Lim, Heui Seok.

In: Journal of Information Science, 01.02.2017.

Research output: Contribution to journalArticle

@article{7898ecf6061a4e9785b0548c8e791c90,
title = "Developing a hybrid collaborative filtering recommendation system with opinion mining on purchase review",
abstract = "The most commonly used algorithm in recommendation systems is collaborative filtering. However, despite its wide use, the prediction accuracy of this algorithm is unexceptional. Furthermore, whether quantitative data such as product rating or purchase history reflect users’ actual taste is questionable. In this article, we propose a method to utilise user review data extracted with opinion mining for product recommendation systems. To evaluate the proposed method, we perform product recommendation test on Amazon product data, with and without the additional opinion mining result on Amazon purchase review data. The performances of these two variants are compared by means of precision, recall, true positive recommendation (TPR) and false positive recommendation (FPR). In this comparison, a large improvement in prediction accuracy was observed when the opinion mining data were taken into account. Based on these results, we answer two main questions: ‘Why is collaborative filtering algorithm not effective?’ and ‘Do quantitative data such as product rating or purchase history reflect users’ actual tastes?’",
keywords = "Collaborative filtering, hybrid recommendation system, opinion mining, purchase review",
author = "Youdong Yun and Danial Hooshyar and Jaechoon Jo and Lim, {Heui Seok}",
year = "2017",
month = "2",
day = "1",
doi = "10.1177/0165551517692955",
language = "English",
journal = "Journal of Information Science",
issn = "0165-5515",
publisher = "SAGE Publications Ltd",

}

TY - JOUR

T1 - Developing a hybrid collaborative filtering recommendation system with opinion mining on purchase review

AU - Yun, Youdong

AU - Hooshyar, Danial

AU - Jo, Jaechoon

AU - Lim, Heui Seok

PY - 2017/2/1

Y1 - 2017/2/1

N2 - The most commonly used algorithm in recommendation systems is collaborative filtering. However, despite its wide use, the prediction accuracy of this algorithm is unexceptional. Furthermore, whether quantitative data such as product rating or purchase history reflect users’ actual taste is questionable. In this article, we propose a method to utilise user review data extracted with opinion mining for product recommendation systems. To evaluate the proposed method, we perform product recommendation test on Amazon product data, with and without the additional opinion mining result on Amazon purchase review data. The performances of these two variants are compared by means of precision, recall, true positive recommendation (TPR) and false positive recommendation (FPR). In this comparison, a large improvement in prediction accuracy was observed when the opinion mining data were taken into account. Based on these results, we answer two main questions: ‘Why is collaborative filtering algorithm not effective?’ and ‘Do quantitative data such as product rating or purchase history reflect users’ actual tastes?’

AB - The most commonly used algorithm in recommendation systems is collaborative filtering. However, despite its wide use, the prediction accuracy of this algorithm is unexceptional. Furthermore, whether quantitative data such as product rating or purchase history reflect users’ actual taste is questionable. In this article, we propose a method to utilise user review data extracted with opinion mining for product recommendation systems. To evaluate the proposed method, we perform product recommendation test on Amazon product data, with and without the additional opinion mining result on Amazon purchase review data. The performances of these two variants are compared by means of precision, recall, true positive recommendation (TPR) and false positive recommendation (FPR). In this comparison, a large improvement in prediction accuracy was observed when the opinion mining data were taken into account. Based on these results, we answer two main questions: ‘Why is collaborative filtering algorithm not effective?’ and ‘Do quantitative data such as product rating or purchase history reflect users’ actual tastes?’

KW - Collaborative filtering

KW - hybrid recommendation system

KW - opinion mining

KW - purchase review

UR - http://www.scopus.com/inward/record.url?scp=85032688264&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032688264&partnerID=8YFLogxK

U2 - 10.1177/0165551517692955

DO - 10.1177/0165551517692955

M3 - Article

AN - SCOPUS:85032688264

JO - Journal of Information Science

JF - Journal of Information Science

SN - 0165-5515

ER -