Feasibility of Using Rating to Predict Sentiment for Online Reviews

Azreen Azman, Eissa M. Alshari, Puteri Suhaiza Sulaiman, Muhamad Taufik Abdullah, Mostafa Alksher, Abdul Kadir Rabiah

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

Abstract

More consumers depend on online recommendation for products before making purchase decision. Comments or ratings given by other online users are used as recommendation and help consumers to make informed decision. Giving rating is a more convenient way to express sentiment toward a product while comments provide details and allow for subjective judgment. This paper investigates the problem of using rating alone to infer the actual sentiment polarity of the raters towards a product. In particular, the experiment attempts to discover whether the lower ratings (1 or 2 in 5-point scale) are more associated to negative polarity while the higher ratings (4 or 5 in 5-point scale) are more associated to positive polarity as universally assumed. A lexical based sentiment analysis approach is used to determine sentiment polarity of each textual comment. The results showed that higher ratings could indicate positive sentiment but it is not the case for the lower ratings in representing negative sentiment.

Original languageEnglish
Title of host publicationAMS 2017 - Asia Modelling Symposium 2017 and 11th International Conference on Mathematical Modelling and Computer Simulation
EditorsZuwairie Ibrahim, David Al-Dabass, Mohd Ibrahim Shapiai
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages37-41
Number of pages5
ISBN (Print)9781538637524
DOIs
Publication statusPublished - 1 Aug 2018
Event2017 Asia Modelling Symposium, AMS 2017 and 11th International Conference on Mathematical Modelling and Computer Simulation - Kota Kinabalu, Sabah, Malaysia
Duration: 4 Dec 20176 Dec 2017

Other

Other2017 Asia Modelling Symposium, AMS 2017 and 11th International Conference on Mathematical Modelling and Computer Simulation
CountryMalaysia
CityKota Kinabalu, Sabah
Period4/12/176/12/17

Fingerprint

Personnel rating
Polarity
Decision making
Predict
Recommendations
Experiments
Sentiment Analysis
Express
Decision Making
Review
Experiment

Keywords

  • opinion word
  • product review
  • sentiment analysis
  • star rating

ASJC Scopus subject areas

  • Computer Science Applications
  • Modelling and Simulation

Cite this

Azman, A., Alshari, E. M., Sulaiman, P. S., Abdullah, M. T., Alksher, M., & Rabiah, A. K. (2018). Feasibility of Using Rating to Predict Sentiment for Online Reviews. In Z. Ibrahim, D. Al-Dabass, & M. I. Shapiai (Eds.), AMS 2017 - Asia Modelling Symposium 2017 and 11th International Conference on Mathematical Modelling and Computer Simulation (pp. 37-41). [8424304] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AMS.2017.14

Feasibility of Using Rating to Predict Sentiment for Online Reviews. / Azman, Azreen; Alshari, Eissa M.; Sulaiman, Puteri Suhaiza; Abdullah, Muhamad Taufik; Alksher, Mostafa; Rabiah, Abdul Kadir.

AMS 2017 - Asia Modelling Symposium 2017 and 11th International Conference on Mathematical Modelling and Computer Simulation. ed. / Zuwairie Ibrahim; David Al-Dabass; Mohd Ibrahim Shapiai. Institute of Electrical and Electronics Engineers Inc., 2018. p. 37-41 8424304.

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

Azman, A, Alshari, EM, Sulaiman, PS, Abdullah, MT, Alksher, M & Rabiah, AK 2018, Feasibility of Using Rating to Predict Sentiment for Online Reviews. in Z Ibrahim, D Al-Dabass & MI Shapiai (eds), AMS 2017 - Asia Modelling Symposium 2017 and 11th International Conference on Mathematical Modelling and Computer Simulation., 8424304, Institute of Electrical and Electronics Engineers Inc., pp. 37-41, 2017 Asia Modelling Symposium, AMS 2017 and 11th International Conference on Mathematical Modelling and Computer Simulation, Kota Kinabalu, Sabah, Malaysia, 4/12/17. https://doi.org/10.1109/AMS.2017.14
Azman A, Alshari EM, Sulaiman PS, Abdullah MT, Alksher M, Rabiah AK. Feasibility of Using Rating to Predict Sentiment for Online Reviews. In Ibrahim Z, Al-Dabass D, Shapiai MI, editors, AMS 2017 - Asia Modelling Symposium 2017 and 11th International Conference on Mathematical Modelling and Computer Simulation. Institute of Electrical and Electronics Engineers Inc. 2018. p. 37-41. 8424304 https://doi.org/10.1109/AMS.2017.14
Azman, Azreen ; Alshari, Eissa M. ; Sulaiman, Puteri Suhaiza ; Abdullah, Muhamad Taufik ; Alksher, Mostafa ; Rabiah, Abdul Kadir. / Feasibility of Using Rating to Predict Sentiment for Online Reviews. AMS 2017 - Asia Modelling Symposium 2017 and 11th International Conference on Mathematical Modelling and Computer Simulation. editor / Zuwairie Ibrahim ; David Al-Dabass ; Mohd Ibrahim Shapiai. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 37-41
@inproceedings{0e3ae48a4c6c4597821c9aad72bf5256,
title = "Feasibility of Using Rating to Predict Sentiment for Online Reviews",
abstract = "More consumers depend on online recommendation for products before making purchase decision. Comments or ratings given by other online users are used as recommendation and help consumers to make informed decision. Giving rating is a more convenient way to express sentiment toward a product while comments provide details and allow for subjective judgment. This paper investigates the problem of using rating alone to infer the actual sentiment polarity of the raters towards a product. In particular, the experiment attempts to discover whether the lower ratings (1 or 2 in 5-point scale) are more associated to negative polarity while the higher ratings (4 or 5 in 5-point scale) are more associated to positive polarity as universally assumed. A lexical based sentiment analysis approach is used to determine sentiment polarity of each textual comment. The results showed that higher ratings could indicate positive sentiment but it is not the case for the lower ratings in representing negative sentiment.",
keywords = "opinion word, product review, sentiment analysis, star rating",
author = "Azreen Azman and Alshari, {Eissa M.} and Sulaiman, {Puteri Suhaiza} and Abdullah, {Muhamad Taufik} and Mostafa Alksher and Rabiah, {Abdul Kadir}",
year = "2018",
month = "8",
day = "1",
doi = "10.1109/AMS.2017.14",
language = "English",
isbn = "9781538637524",
pages = "37--41",
editor = "Zuwairie Ibrahim and David Al-Dabass and Shapiai, {Mohd Ibrahim}",
booktitle = "AMS 2017 - Asia Modelling Symposium 2017 and 11th International Conference on Mathematical Modelling and Computer Simulation",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Feasibility of Using Rating to Predict Sentiment for Online Reviews

AU - Azman, Azreen

AU - Alshari, Eissa M.

AU - Sulaiman, Puteri Suhaiza

AU - Abdullah, Muhamad Taufik

AU - Alksher, Mostafa

AU - Rabiah, Abdul Kadir

PY - 2018/8/1

Y1 - 2018/8/1

N2 - More consumers depend on online recommendation for products before making purchase decision. Comments or ratings given by other online users are used as recommendation and help consumers to make informed decision. Giving rating is a more convenient way to express sentiment toward a product while comments provide details and allow for subjective judgment. This paper investigates the problem of using rating alone to infer the actual sentiment polarity of the raters towards a product. In particular, the experiment attempts to discover whether the lower ratings (1 or 2 in 5-point scale) are more associated to negative polarity while the higher ratings (4 or 5 in 5-point scale) are more associated to positive polarity as universally assumed. A lexical based sentiment analysis approach is used to determine sentiment polarity of each textual comment. The results showed that higher ratings could indicate positive sentiment but it is not the case for the lower ratings in representing negative sentiment.

AB - More consumers depend on online recommendation for products before making purchase decision. Comments or ratings given by other online users are used as recommendation and help consumers to make informed decision. Giving rating is a more convenient way to express sentiment toward a product while comments provide details and allow for subjective judgment. This paper investigates the problem of using rating alone to infer the actual sentiment polarity of the raters towards a product. In particular, the experiment attempts to discover whether the lower ratings (1 or 2 in 5-point scale) are more associated to negative polarity while the higher ratings (4 or 5 in 5-point scale) are more associated to positive polarity as universally assumed. A lexical based sentiment analysis approach is used to determine sentiment polarity of each textual comment. The results showed that higher ratings could indicate positive sentiment but it is not the case for the lower ratings in representing negative sentiment.

KW - opinion word

KW - product review

KW - sentiment analysis

KW - star rating

UR - http://www.scopus.com/inward/record.url?scp=85051488373&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85051488373&partnerID=8YFLogxK

U2 - 10.1109/AMS.2017.14

DO - 10.1109/AMS.2017.14

M3 - Conference contribution

SN - 9781538637524

SP - 37

EP - 41

BT - AMS 2017 - Asia Modelling Symposium 2017 and 11th International Conference on Mathematical Modelling and Computer Simulation

A2 - Ibrahim, Zuwairie

A2 - Al-Dabass, David

A2 - Shapiai, Mohd Ibrahim

PB - Institute of Electrical and Electronics Engineers Inc.

ER -