ANR: Aspect-based Neural Recommender

Jin Yao Chin, Shafiq Rayhan Joty, Kaiqi Zhao, Gao Cong

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

12 Citations (Scopus)

Abstract

Textual reviews, which are readily available on many e-commerce and review websites such as Amazon and Yelp, serve as an invaluable source of information for recommender systems. However, not all parts of the reviews are equally important, and the same choice of words may reflect a different meaning based on its context. In this paper, we propose a novel end-to-end Aspect-based Neural Recommender (ANR) to perform aspect-based representation learning for both users and items via an attention-based component. Furthermore, we model the multi-faceted process behind how users rate items by estimating the aspect-level user and item importance based on the neural co-attention mechanism. Our proposed model concurrently address several shortcomings of existing recommender systems, and a thorough experimental study on 25 benchmark datasets from Amazon and Yelp shows that ANR significantly outperforms recently proposed state-of-the-art baselines such as DeepCoNN, D-Attn and ALFM.

Original languageEnglish
Title of host publicationCIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management
EditorsNorman Paton, Selcuk Candan, Haixun Wang, James Allan, Rakesh Agrawal, Alexandros Labrinidis, Alfredo Cuzzocrea, Mohammed Zaki, Divesh Srivastava, Andrei Broder, Assaf Schuster
PublisherAssociation for Computing Machinery
Pages147-156
Number of pages10
ISBN (Electronic)9781450360142
DOIs
Publication statusPublished - 17 Oct 2018
Event27th ACM International Conference on Information and Knowledge Management, CIKM 2018 - Torino, Italy
Duration: 22 Oct 201826 Oct 2018

Other

Other27th ACM International Conference on Information and Knowledge Management, CIKM 2018
CountryItaly
CityTorino
Period22/10/1826/10/18

Fingerprint

Recommender systems
Amazon
Benchmark
Sources of information
Electronic commerce
Web sites
Experimental study

Keywords

  • Aspect-based Recommendation
  • Co-Attention
  • Neural Attention
  • Recommender Systems

ASJC Scopus subject areas

  • Business, Management and Accounting(all)
  • Decision Sciences(all)

Cite this

Chin, J. Y., Rayhan Joty, S., Zhao, K., & Cong, G. (2018). ANR: Aspect-based Neural Recommender. In N. Paton, S. Candan, H. Wang, J. Allan, R. Agrawal, A. Labrinidis, A. Cuzzocrea, M. Zaki, D. Srivastava, A. Broder, ... A. Schuster (Eds.), CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management (pp. 147-156). Association for Computing Machinery. https://doi.org/10.1145/3269206.3271810

ANR : Aspect-based Neural Recommender. / Chin, Jin Yao; Rayhan Joty, Shafiq; Zhao, Kaiqi; Cong, Gao.

CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management. ed. / Norman Paton; Selcuk Candan; Haixun Wang; James Allan; Rakesh Agrawal; Alexandros Labrinidis; Alfredo Cuzzocrea; Mohammed Zaki; Divesh Srivastava; Andrei Broder; Assaf Schuster. Association for Computing Machinery, 2018. p. 147-156.

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

Chin, JY, Rayhan Joty, S, Zhao, K & Cong, G 2018, ANR: Aspect-based Neural Recommender. in N Paton, S Candan, H Wang, J Allan, R Agrawal, A Labrinidis, A Cuzzocrea, M Zaki, D Srivastava, A Broder & A Schuster (eds), CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, pp. 147-156, 27th ACM International Conference on Information and Knowledge Management, CIKM 2018, Torino, Italy, 22/10/18. https://doi.org/10.1145/3269206.3271810
Chin JY, Rayhan Joty S, Zhao K, Cong G. ANR: Aspect-based Neural Recommender. In Paton N, Candan S, Wang H, Allan J, Agrawal R, Labrinidis A, Cuzzocrea A, Zaki M, Srivastava D, Broder A, Schuster A, editors, CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery. 2018. p. 147-156 https://doi.org/10.1145/3269206.3271810
Chin, Jin Yao ; Rayhan Joty, Shafiq ; Zhao, Kaiqi ; Cong, Gao. / ANR : Aspect-based Neural Recommender. CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management. editor / Norman Paton ; Selcuk Candan ; Haixun Wang ; James Allan ; Rakesh Agrawal ; Alexandros Labrinidis ; Alfredo Cuzzocrea ; Mohammed Zaki ; Divesh Srivastava ; Andrei Broder ; Assaf Schuster. Association for Computing Machinery, 2018. pp. 147-156
@inproceedings{78502e1fced64edf85fd515706988ef8,
title = "ANR: Aspect-based Neural Recommender",
abstract = "Textual reviews, which are readily available on many e-commerce and review websites such as Amazon and Yelp, serve as an invaluable source of information for recommender systems. However, not all parts of the reviews are equally important, and the same choice of words may reflect a different meaning based on its context. In this paper, we propose a novel end-to-end Aspect-based Neural Recommender (ANR) to perform aspect-based representation learning for both users and items via an attention-based component. Furthermore, we model the multi-faceted process behind how users rate items by estimating the aspect-level user and item importance based on the neural co-attention mechanism. Our proposed model concurrently address several shortcomings of existing recommender systems, and a thorough experimental study on 25 benchmark datasets from Amazon and Yelp shows that ANR significantly outperforms recently proposed state-of-the-art baselines such as DeepCoNN, D-Attn and ALFM.",
keywords = "Aspect-based Recommendation, Co-Attention, Neural Attention, Recommender Systems",
author = "Chin, {Jin Yao} and {Rayhan Joty}, Shafiq and Kaiqi Zhao and Gao Cong",
year = "2018",
month = "10",
day = "17",
doi = "10.1145/3269206.3271810",
language = "English",
pages = "147--156",
editor = "Norman Paton and Selcuk Candan and Haixun Wang and James Allan and Rakesh Agrawal and Alexandros Labrinidis and Alfredo Cuzzocrea and Mohammed Zaki and Divesh Srivastava and Andrei Broder and Assaf Schuster",
booktitle = "CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - ANR

T2 - Aspect-based Neural Recommender

AU - Chin, Jin Yao

AU - Rayhan Joty, Shafiq

AU - Zhao, Kaiqi

AU - Cong, Gao

PY - 2018/10/17

Y1 - 2018/10/17

N2 - Textual reviews, which are readily available on many e-commerce and review websites such as Amazon and Yelp, serve as an invaluable source of information for recommender systems. However, not all parts of the reviews are equally important, and the same choice of words may reflect a different meaning based on its context. In this paper, we propose a novel end-to-end Aspect-based Neural Recommender (ANR) to perform aspect-based representation learning for both users and items via an attention-based component. Furthermore, we model the multi-faceted process behind how users rate items by estimating the aspect-level user and item importance based on the neural co-attention mechanism. Our proposed model concurrently address several shortcomings of existing recommender systems, and a thorough experimental study on 25 benchmark datasets from Amazon and Yelp shows that ANR significantly outperforms recently proposed state-of-the-art baselines such as DeepCoNN, D-Attn and ALFM.

AB - Textual reviews, which are readily available on many e-commerce and review websites such as Amazon and Yelp, serve as an invaluable source of information for recommender systems. However, not all parts of the reviews are equally important, and the same choice of words may reflect a different meaning based on its context. In this paper, we propose a novel end-to-end Aspect-based Neural Recommender (ANR) to perform aspect-based representation learning for both users and items via an attention-based component. Furthermore, we model the multi-faceted process behind how users rate items by estimating the aspect-level user and item importance based on the neural co-attention mechanism. Our proposed model concurrently address several shortcomings of existing recommender systems, and a thorough experimental study on 25 benchmark datasets from Amazon and Yelp shows that ANR significantly outperforms recently proposed state-of-the-art baselines such as DeepCoNN, D-Attn and ALFM.

KW - Aspect-based Recommendation

KW - Co-Attention

KW - Neural Attention

KW - Recommender Systems

UR - http://www.scopus.com/inward/record.url?scp=85058014698&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058014698&partnerID=8YFLogxK

U2 - 10.1145/3269206.3271810

DO - 10.1145/3269206.3271810

M3 - Conference contribution

AN - SCOPUS:85058014698

SP - 147

EP - 156

BT - CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management

A2 - Paton, Norman

A2 - Candan, Selcuk

A2 - Wang, Haixun

A2 - Allan, James

A2 - Agrawal, Rakesh

A2 - Labrinidis, Alexandros

A2 - Cuzzocrea, Alfredo

A2 - Zaki, Mohammed

A2 - Srivastava, Divesh

A2 - Broder, Andrei

A2 - Schuster, Assaf

PB - Association for Computing Machinery

ER -