Impact Rating Scales on Recommender System and Using Deep Learning and Neural Network Models to Improve Rating Prediction

Maram Almaghrabi, Girija Chetty

Research output: A Conference proceeding or a Chapter in BookConference contribution

Abstract

A lot of websites enables users to have the ability to rank products and share their rankings with other users for personalization or social resolutions. In specific the recommender systems, personalization recommendations are produced by forecasting ratings for products which users are insensitive of, grounded on the scores users offered for various commodities. Explicit consumer ratings are composed by way of graphical widgets known as a rating scale. Every website or system usually applies a certain rating scale in several instances opposing from scales applied by other networks in their numbering, granularity, existing of neutral position or visual metaphor. Several tasks in the area of survey design testified on the impact of ranking scales on consumer ratings, these, though, are usually considered impartial tools when in recommender systems. This paper offers novel empirical data on the impact of rating scales on consumer ratings. We describe how the rating scale can affect the recommendation system user performance. In addition, we propose a novel approach based on deep learning-based augmentation of the collaborative filtering approach with deep neural networks for discovering the complex and deep interactions in the shared space between users, and ratings/reviews, and provide significant improvement for predicting user ratings.

Original languageEnglish
Title of host publicationProceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018
Subtitle of host publicationAPWConCSE 2018
EditorsA B M Shawkat Ali, Shah Miah, Maheswara Rao Valluri
Place of PublicationDanvers, USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages207-213
Number of pages7
ISBN (Electronic)9781728113906
ISBN (Print)9781728113906
DOIs
Publication statusPublished - 1 Dec 2018
Event5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018 - Nadi, Fiji
Duration: 10 Dec 201812 Dec 2018

Publication series

NameProceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018

Conference

Conference5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018
CountryFiji
CityNadi
Period10/12/1812/12/18

Fingerprint

Metaphor
Aptitude
Neural Networks (Computer)
Recommender systems
Learning
Neural networks
Websites
Collaborative filtering
Surveys and Questionnaires
Deep learning

Cite this

Almaghrabi, M., & Chetty, G. (2018). Impact Rating Scales on Recommender System and Using Deep Learning and Neural Network Models to Improve Rating Prediction. In A. B. M. S. Ali, S. Miah, & M. Rao Valluri (Eds.), Proceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018: APWConCSE 2018 (pp. 207-213). [8853658] (Proceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018). Danvers, USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/apwconcse.2018.00041
Almaghrabi, Maram ; Chetty, Girija. / Impact Rating Scales on Recommender System and Using Deep Learning and Neural Network Models to Improve Rating Prediction. Proceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018: APWConCSE 2018 . editor / A B M Shawkat Ali ; Shah Miah ; Maheswara Rao Valluri. Danvers, USA : IEEE, Institute of Electrical and Electronics Engineers, 2018. pp. 207-213 (Proceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018).
@inproceedings{6b16d6becb744e4491193d205edfbbe8,
title = "Impact Rating Scales on Recommender System and Using Deep Learning and Neural Network Models to Improve Rating Prediction",
abstract = "A lot of websites enables users to have the ability to rank products and share their rankings with other users for personalization or social resolutions. In specific the recommender systems, personalization recommendations are produced by forecasting ratings for products which users are insensitive of, grounded on the scores users offered for various commodities. Explicit consumer ratings are composed by way of graphical widgets known as a rating scale. Every website or system usually applies a certain rating scale in several instances opposing from scales applied by other networks in their numbering, granularity, existing of neutral position or visual metaphor. Several tasks in the area of survey design testified on the impact of ranking scales on consumer ratings, these, though, are usually considered impartial tools when in recommender systems. This paper offers novel empirical data on the impact of rating scales on consumer ratings. We describe how the rating scale can affect the recommendation system user performance. In addition, we propose a novel approach based on deep learning-based augmentation of the collaborative filtering approach with deep neural networks for discovering the complex and deep interactions in the shared space between users, and ratings/reviews, and provide significant improvement for predicting user ratings.",
keywords = "Collaborative filtering, Deep learning, Neural Network, Rating Scale, Recommender system",
author = "Maram Almaghrabi and Girija Chetty",
year = "2018",
month = "12",
day = "1",
doi = "10.1109/apwconcse.2018.00041",
language = "English",
isbn = "9781728113906",
series = "Proceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
pages = "207--213",
editor = "Ali, {A B M Shawkat } and Shah Miah and {Rao Valluri}, {Maheswara }",
booktitle = "Proceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018",
address = "United States",

}

Almaghrabi, M & Chetty, G 2018, Impact Rating Scales on Recommender System and Using Deep Learning and Neural Network Models to Improve Rating Prediction. in ABMS Ali, S Miah & M Rao Valluri (eds), Proceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018: APWConCSE 2018 ., 8853658, Proceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018, IEEE, Institute of Electrical and Electronics Engineers, Danvers, USA, pp. 207-213, 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018, Nadi, Fiji, 10/12/18. https://doi.org/10.1109/apwconcse.2018.00041

Impact Rating Scales on Recommender System and Using Deep Learning and Neural Network Models to Improve Rating Prediction. / Almaghrabi, Maram; Chetty, Girija.

Proceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018: APWConCSE 2018 . ed. / A B M Shawkat Ali; Shah Miah; Maheswara Rao Valluri. Danvers, USA : IEEE, Institute of Electrical and Electronics Engineers, 2018. p. 207-213 8853658 (Proceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018).

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Impact Rating Scales on Recommender System and Using Deep Learning and Neural Network Models to Improve Rating Prediction

AU - Almaghrabi, Maram

AU - Chetty, Girija

PY - 2018/12/1

Y1 - 2018/12/1

N2 - A lot of websites enables users to have the ability to rank products and share their rankings with other users for personalization or social resolutions. In specific the recommender systems, personalization recommendations are produced by forecasting ratings for products which users are insensitive of, grounded on the scores users offered for various commodities. Explicit consumer ratings are composed by way of graphical widgets known as a rating scale. Every website or system usually applies a certain rating scale in several instances opposing from scales applied by other networks in their numbering, granularity, existing of neutral position or visual metaphor. Several tasks in the area of survey design testified on the impact of ranking scales on consumer ratings, these, though, are usually considered impartial tools when in recommender systems. This paper offers novel empirical data on the impact of rating scales on consumer ratings. We describe how the rating scale can affect the recommendation system user performance. In addition, we propose a novel approach based on deep learning-based augmentation of the collaborative filtering approach with deep neural networks for discovering the complex and deep interactions in the shared space between users, and ratings/reviews, and provide significant improvement for predicting user ratings.

AB - A lot of websites enables users to have the ability to rank products and share their rankings with other users for personalization or social resolutions. In specific the recommender systems, personalization recommendations are produced by forecasting ratings for products which users are insensitive of, grounded on the scores users offered for various commodities. Explicit consumer ratings are composed by way of graphical widgets known as a rating scale. Every website or system usually applies a certain rating scale in several instances opposing from scales applied by other networks in their numbering, granularity, existing of neutral position or visual metaphor. Several tasks in the area of survey design testified on the impact of ranking scales on consumer ratings, these, though, are usually considered impartial tools when in recommender systems. This paper offers novel empirical data on the impact of rating scales on consumer ratings. We describe how the rating scale can affect the recommendation system user performance. In addition, we propose a novel approach based on deep learning-based augmentation of the collaborative filtering approach with deep neural networks for discovering the complex and deep interactions in the shared space between users, and ratings/reviews, and provide significant improvement for predicting user ratings.

KW - Collaborative filtering

KW - Deep learning

KW - Neural Network

KW - Rating Scale

KW - Recommender system

UR - http://www.scopus.com/inward/record.url?scp=85074297137&partnerID=8YFLogxK

UR - http://www.mendeley.com/research/impact-rating-scales-recommender-system-using-deep-learning-neural-network-models-improve-rating-pre

U2 - 10.1109/apwconcse.2018.00041

DO - 10.1109/apwconcse.2018.00041

M3 - Conference contribution

SN - 9781728113906

T3 - Proceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018

SP - 207

EP - 213

BT - Proceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018

A2 - Ali, A B M Shawkat

A2 - Miah, Shah

A2 - Rao Valluri, Maheswara

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Danvers, USA

ER -

Almaghrabi M, Chetty G. Impact Rating Scales on Recommender System and Using Deep Learning and Neural Network Models to Improve Rating Prediction. In Ali ABMS, Miah S, Rao Valluri M, editors, Proceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018: APWConCSE 2018 . Danvers, USA: IEEE, Institute of Electrical and Electronics Engineers. 2018. p. 207-213. 8853658. (Proceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018). https://doi.org/10.1109/apwconcse.2018.00041