Contextual sentiment based recommender system to provide recommendation in the electronic products domain

N. A. Osman, Shahrul Azman Mohd Noah, M. Darwich

Research output: Contribution to journalArticle

Abstract

The rush to purchase the latest products sometimes prevents people from thinking things through completely. Consequently, recommender services are increasingly emerging. By looking at industry trends, interviewing dozens of leading industry stakeholders, and using publicly available information, it is important to filter out the most relevant information for consumer electronics before purchasing their items. This paper presents an electronic product recommender system based on contextual information from sentiment analysis. The recommendation algorithms mostly rely on users' rating to make prediction of items. Such ratings are usually insufficient and very limited. We present a contextual information sentiment based model for recommender system by making use of user comments and preferences to provide a recommendation. The purpose of this approach is to avoid term ambiguity which is so called domain sensitivity problem in recommendation. The proposed contextual information sentiment-based model illustrates better performance by using results of RMSE and MAE measurements as compared to the conventional collaborative filtering approach in electronic product recommendation.

Original languageEnglish
Pages (from-to)425-431
Number of pages7
JournalInternational Journal of Machine Learning and Computing
Volume9
Issue number4
DOIs
Publication statusPublished - 1 Aug 2019

Fingerprint

Recommender systems
Collaborative filtering
Consumer electronics
Purchasing
Industry
Sentiment
Rating

Keywords

  • Collaborative filtering
  • Domain sensitivity
  • Electronic product
  • Recommender systems
  • Sentiment analysis

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems and Management
  • Artificial Intelligence

Cite this

Contextual sentiment based recommender system to provide recommendation in the electronic products domain. / Osman, N. A.; Mohd Noah, Shahrul Azman; Darwich, M.

In: International Journal of Machine Learning and Computing, Vol. 9, No. 4, 01.08.2019, p. 425-431.

Research output: Contribution to journalArticle

@article{c584726d9d10470aaed57c7a17d5f133,
title = "Contextual sentiment based recommender system to provide recommendation in the electronic products domain",
abstract = "The rush to purchase the latest products sometimes prevents people from thinking things through completely. Consequently, recommender services are increasingly emerging. By looking at industry trends, interviewing dozens of leading industry stakeholders, and using publicly available information, it is important to filter out the most relevant information for consumer electronics before purchasing their items. This paper presents an electronic product recommender system based on contextual information from sentiment analysis. The recommendation algorithms mostly rely on users' rating to make prediction of items. Such ratings are usually insufficient and very limited. We present a contextual information sentiment based model for recommender system by making use of user comments and preferences to provide a recommendation. The purpose of this approach is to avoid term ambiguity which is so called domain sensitivity problem in recommendation. The proposed contextual information sentiment-based model illustrates better performance by using results of RMSE and MAE measurements as compared to the conventional collaborative filtering approach in electronic product recommendation.",
keywords = "Collaborative filtering, Domain sensitivity, Electronic product, Recommender systems, Sentiment analysis",
author = "Osman, {N. A.} and {Mohd Noah}, {Shahrul Azman} and M. Darwich",
year = "2019",
month = "8",
day = "1",
doi = "10.18178/ijmlc.2019.9.4.821",
language = "English",
volume = "9",
pages = "425--431",
journal = "International Journal of Machine Learning and Computing",
issn = "2010-3700",
publisher = "International Association of Computer Science and Information Technology",
number = "4",

}

TY - JOUR

T1 - Contextual sentiment based recommender system to provide recommendation in the electronic products domain

AU - Osman, N. A.

AU - Mohd Noah, Shahrul Azman

AU - Darwich, M.

PY - 2019/8/1

Y1 - 2019/8/1

N2 - The rush to purchase the latest products sometimes prevents people from thinking things through completely. Consequently, recommender services are increasingly emerging. By looking at industry trends, interviewing dozens of leading industry stakeholders, and using publicly available information, it is important to filter out the most relevant information for consumer electronics before purchasing their items. This paper presents an electronic product recommender system based on contextual information from sentiment analysis. The recommendation algorithms mostly rely on users' rating to make prediction of items. Such ratings are usually insufficient and very limited. We present a contextual information sentiment based model for recommender system by making use of user comments and preferences to provide a recommendation. The purpose of this approach is to avoid term ambiguity which is so called domain sensitivity problem in recommendation. The proposed contextual information sentiment-based model illustrates better performance by using results of RMSE and MAE measurements as compared to the conventional collaborative filtering approach in electronic product recommendation.

AB - The rush to purchase the latest products sometimes prevents people from thinking things through completely. Consequently, recommender services are increasingly emerging. By looking at industry trends, interviewing dozens of leading industry stakeholders, and using publicly available information, it is important to filter out the most relevant information for consumer electronics before purchasing their items. This paper presents an electronic product recommender system based on contextual information from sentiment analysis. The recommendation algorithms mostly rely on users' rating to make prediction of items. Such ratings are usually insufficient and very limited. We present a contextual information sentiment based model for recommender system by making use of user comments and preferences to provide a recommendation. The purpose of this approach is to avoid term ambiguity which is so called domain sensitivity problem in recommendation. The proposed contextual information sentiment-based model illustrates better performance by using results of RMSE and MAE measurements as compared to the conventional collaborative filtering approach in electronic product recommendation.

KW - Collaborative filtering

KW - Domain sensitivity

KW - Electronic product

KW - Recommender systems

KW - Sentiment analysis

UR - http://www.scopus.com/inward/record.url?scp=85071321959&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071321959&partnerID=8YFLogxK

U2 - 10.18178/ijmlc.2019.9.4.821

DO - 10.18178/ijmlc.2019.9.4.821

M3 - Article

AN - SCOPUS:85071321959

VL - 9

SP - 425

EP - 431

JO - International Journal of Machine Learning and Computing

JF - International Journal of Machine Learning and Computing

SN - 2010-3700

IS - 4

ER -