Tensorized neural network for multi-aspect rating-based recommendation
Generating personalized recommendations is one of the most crucial aspects in Recommender System research area. Most of the researches only focus on the accuracy of recommendation using collaborative filtering that relies on a single overall rating that repres...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Blue Eyes Intelligence Engineering & Sciences Publication
2019
|
Online Access: | http://psasir.upm.edu.my/id/eprint/82153/1/Tensorized%20neural.pdf http://psasir.upm.edu.my/id/eprint/82153/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.upm.eprints.82153 |
---|---|
record_format |
eprints |
spelling |
my.upm.eprints.821532020-10-17T20:19:57Z http://psasir.upm.edu.my/id/eprint/82153/ Tensorized neural network for multi-aspect rating-based recommendation Khairudin, Nurkhairizan Mohd Sharef, Nurfadhlina Mohd Noah, Shahrul Azman Mustapha, Norwati Generating personalized recommendations is one of the most crucial aspects in Recommender System research area. Most of the researches only focus on the accuracy of recommendation using collaborative filtering that relies on a single overall rating that represents the overall preferences. However, the user may have a different emphasis on different specific aspects that affect the users’ final rating decisions. Therefore, we present a neural network model that utilize multi-aspects ratings using Tensor Factorization to improve the accuracy of personalization, as well as optimizing the dynamic weights of the aspect. To measure the estimated weights for the aspects, we employ the Higher Order Singular Value Decomposition (HOSVD) technique called CANDECOMP/PARAFAC (CP) decomposition that allows for multi-faceted data processing. We then develop the Neural Network with back propagation error to train the model with different parameter settings and limited computational time. We also use a non-linear activation function in each hidden layer in various settings. The experimental result measured using MAE shows that the proposed model has significantly out performed the baseline approach in terms of the prediction accuracy. Based on the observation, the performance of rating prediction has been improved by employing the Tensorized Neural Network model and can overcome the problem of local optimum convergence for multi-aspect rating recommendation. Blue Eyes Intelligence Engineering & Sciences Publication 2019-09 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/82153/1/Tensorized%20neural.pdf Khairudin, Nurkhairizan and Mohd Sharef, Nurfadhlina and Mohd Noah, Shahrul Azman and Mustapha, Norwati (2019) Tensorized neural network for multi-aspect rating-based recommendation. International Journal of Recent Technology and Engineering, 8 (2s11). pp. 547-551. ISSN 2277-3878 10.35940/ijrte.B1085.0982S1119 |
institution |
Universiti Putra Malaysia |
building |
UPM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Putra Malaysia |
content_source |
UPM Institutional Repository |
url_provider |
http://psasir.upm.edu.my/ |
language |
English |
description |
Generating personalized recommendations is one of the most crucial aspects in Recommender System research area. Most of the researches only focus on the accuracy of recommendation using collaborative filtering that relies on a single overall rating that represents the overall preferences. However, the user may have a different emphasis on different specific aspects that affect the users’ final rating decisions. Therefore, we present a neural network model that utilize multi-aspects ratings using Tensor Factorization to improve the accuracy of personalization, as well as optimizing the dynamic weights of the aspect. To measure the estimated weights for the aspects, we employ the Higher Order Singular Value Decomposition (HOSVD) technique called CANDECOMP/PARAFAC (CP) decomposition that allows for multi-faceted data processing. We then develop the Neural Network with back propagation error to train the model with different parameter settings and limited computational time. We also use a non-linear activation function in each hidden layer in various settings. The experimental result measured using MAE shows that the proposed model has significantly out performed the baseline approach in terms of the prediction accuracy. Based on the observation, the performance of rating prediction has been improved by employing the Tensorized Neural Network model and can overcome the problem of local optimum convergence for multi-aspect rating recommendation. |
format |
Article |
author |
Khairudin, Nurkhairizan Mohd Sharef, Nurfadhlina Mohd Noah, Shahrul Azman Mustapha, Norwati |
spellingShingle |
Khairudin, Nurkhairizan Mohd Sharef, Nurfadhlina Mohd Noah, Shahrul Azman Mustapha, Norwati Tensorized neural network for multi-aspect rating-based recommendation |
author_facet |
Khairudin, Nurkhairizan Mohd Sharef, Nurfadhlina Mohd Noah, Shahrul Azman Mustapha, Norwati |
author_sort |
Khairudin, Nurkhairizan |
title |
Tensorized neural network for multi-aspect rating-based recommendation |
title_short |
Tensorized neural network for multi-aspect rating-based recommendation |
title_full |
Tensorized neural network for multi-aspect rating-based recommendation |
title_fullStr |
Tensorized neural network for multi-aspect rating-based recommendation |
title_full_unstemmed |
Tensorized neural network for multi-aspect rating-based recommendation |
title_sort |
tensorized neural network for multi-aspect rating-based recommendation |
publisher |
Blue Eyes Intelligence Engineering & Sciences Publication |
publishDate |
2019 |
url |
http://psasir.upm.edu.my/id/eprint/82153/1/Tensorized%20neural.pdf http://psasir.upm.edu.my/id/eprint/82153/ |
_version_ |
1681490850863906816 |
score |
13.1944895 |