Rating prediction using feature words extracted from customer reviews

Masanao Ochi, Makoto Okabe, Rikio Onai

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

5 Citations (Scopus)

Abstract

We developed a simple method of improving the accuracy of rating prediction using feature words extracted from customer reviews. Many rating predictors work well for a small and dense dataset of customer reviews. However, a practical dataset tends to be large and sparse, because it often includes too many products for each customer to buy and evaluate. Data sparseness reduces prediction accuracy. To improve accuracy, we reduced the dimension of the feature vector using feature words extracted by analyzing the relationship between ratings and accompanying review comments instead of using ratings. We applied our method to the Pranking algorithm and evaluated it on a corpus of golf course reviews supplied by a Japanese e-commerce company. We found that by successfully reducing data sparse-ness, our method improves prediction accuracy as measured using RankLoss.

Original languageEnglish
Title of host publicationSIGIR'11 - Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval
Pages1205-1206
Number of pages2
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event34th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR'11 - Beijing
Duration: 2011 Jul 242011 Jul 28

Other

Other34th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR'11
CityBeijing
Period11/7/2411/7/28

Fingerprint

Industry

Keywords

  • Rating prediction
  • Review mining
  • Sentiment analysis

ASJC Scopus subject areas

  • Information Systems

Cite this

Ochi, M., Okabe, M., & Onai, R. (2011). Rating prediction using feature words extracted from customer reviews. In SIGIR'11 - Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 1205-1206) https://doi.org/10.1145/2009916.2010121

Rating prediction using feature words extracted from customer reviews. / Ochi, Masanao; Okabe, Makoto; Onai, Rikio.

SIGIR'11 - Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2011. p. 1205-1206.

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

Ochi, M, Okabe, M & Onai, R 2011, Rating prediction using feature words extracted from customer reviews. in SIGIR'11 - Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval. pp. 1205-1206, 34th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR'11, Beijing, 11/7/24. https://doi.org/10.1145/2009916.2010121
Ochi M, Okabe M, Onai R. Rating prediction using feature words extracted from customer reviews. In SIGIR'11 - Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2011. p. 1205-1206 https://doi.org/10.1145/2009916.2010121
Ochi, Masanao ; Okabe, Makoto ; Onai, Rikio. / Rating prediction using feature words extracted from customer reviews. SIGIR'11 - Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2011. pp. 1205-1206
@inproceedings{f2eda296c13b4853b50fa701ed5c53e6,
title = "Rating prediction using feature words extracted from customer reviews",
abstract = "We developed a simple method of improving the accuracy of rating prediction using feature words extracted from customer reviews. Many rating predictors work well for a small and dense dataset of customer reviews. However, a practical dataset tends to be large and sparse, because it often includes too many products for each customer to buy and evaluate. Data sparseness reduces prediction accuracy. To improve accuracy, we reduced the dimension of the feature vector using feature words extracted by analyzing the relationship between ratings and accompanying review comments instead of using ratings. We applied our method to the Pranking algorithm and evaluated it on a corpus of golf course reviews supplied by a Japanese e-commerce company. We found that by successfully reducing data sparse-ness, our method improves prediction accuracy as measured using RankLoss.",
keywords = "Rating prediction, Review mining, Sentiment analysis",
author = "Masanao Ochi and Makoto Okabe and Rikio Onai",
year = "2011",
doi = "10.1145/2009916.2010121",
language = "English",
isbn = "9781450309349",
pages = "1205--1206",
booktitle = "SIGIR'11 - Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval",

}

TY - GEN

T1 - Rating prediction using feature words extracted from customer reviews

AU - Ochi, Masanao

AU - Okabe, Makoto

AU - Onai, Rikio

PY - 2011

Y1 - 2011

N2 - We developed a simple method of improving the accuracy of rating prediction using feature words extracted from customer reviews. Many rating predictors work well for a small and dense dataset of customer reviews. However, a practical dataset tends to be large and sparse, because it often includes too many products for each customer to buy and evaluate. Data sparseness reduces prediction accuracy. To improve accuracy, we reduced the dimension of the feature vector using feature words extracted by analyzing the relationship between ratings and accompanying review comments instead of using ratings. We applied our method to the Pranking algorithm and evaluated it on a corpus of golf course reviews supplied by a Japanese e-commerce company. We found that by successfully reducing data sparse-ness, our method improves prediction accuracy as measured using RankLoss.

AB - We developed a simple method of improving the accuracy of rating prediction using feature words extracted from customer reviews. Many rating predictors work well for a small and dense dataset of customer reviews. However, a practical dataset tends to be large and sparse, because it often includes too many products for each customer to buy and evaluate. Data sparseness reduces prediction accuracy. To improve accuracy, we reduced the dimension of the feature vector using feature words extracted by analyzing the relationship between ratings and accompanying review comments instead of using ratings. We applied our method to the Pranking algorithm and evaluated it on a corpus of golf course reviews supplied by a Japanese e-commerce company. We found that by successfully reducing data sparse-ness, our method improves prediction accuracy as measured using RankLoss.

KW - Rating prediction

KW - Review mining

KW - Sentiment analysis

UR - http://www.scopus.com/inward/record.url?scp=80052105418&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052105418&partnerID=8YFLogxK

U2 - 10.1145/2009916.2010121

DO - 10.1145/2009916.2010121

M3 - Conference contribution

SN - 9781450309349

SP - 1205

EP - 1206

BT - SIGIR'11 - Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval

ER -