Hypergraphs with attention on reviews for explainable recommendation

Given a recommender system based on reviews, the challenges are how to effectively represent the review data and how to explain the produced recommendations. We propose a novel review-specific Hypergraph (HG) model, and further introduce a model-agnostic explainability module. The HG model captures...

Full description

Saved in:
Bibliographic Details
Main Authors: JENDAL, Theis E., LE, Trung Hoang, LAUW, Hady Wirawan, LISSANDRINI, Matteo, DOLOG, Peter, HOSE, Katja
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2024
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/8724
https://ink.library.smu.edu.sg/context/sis_research/article/9727/viewcontent/ecir24.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-9727
record_format dspace
spelling sg-smu-ink.sis_research-97272024-10-17T07:18:35Z Hypergraphs with attention on reviews for explainable recommendation JENDAL, Theis E. LE, Trung Hoang LAUW, Hady Wirawan LISSANDRINI, Matteo DOLOG, Peter HOSE, Katja Given a recommender system based on reviews, the challenges are how to effectively represent the review data and how to explain the produced recommendations. We propose a novel review-specific Hypergraph (HG) model, and further introduce a model-agnostic explainability module. The HG model captures high-order connections between users, items, aspects, and opinions while maintaining information about the review. The explainability module can use the HG model to explain a prediction generated by any model. We propose a path-restricted review-selection method biased by the user preference for item reviews and propose a novel explanation method based on a review graph. Experiments on real-world datasets confirm the ability of the HG model to capture appropriate explanations. 2024-03-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8724 info:doi/10.1007/978-3-031-56027-9_14 https://ink.library.smu.edu.sg/context/sis_research/article/9727/viewcontent/ecir24.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Databases and Information Systems Numerical Analysis and Scientific Computing
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Databases and Information Systems
Numerical Analysis and Scientific Computing
spellingShingle Databases and Information Systems
Numerical Analysis and Scientific Computing
JENDAL, Theis E.
LE, Trung Hoang
LAUW, Hady Wirawan
LISSANDRINI, Matteo
DOLOG, Peter
HOSE, Katja
Hypergraphs with attention on reviews for explainable recommendation
description Given a recommender system based on reviews, the challenges are how to effectively represent the review data and how to explain the produced recommendations. We propose a novel review-specific Hypergraph (HG) model, and further introduce a model-agnostic explainability module. The HG model captures high-order connections between users, items, aspects, and opinions while maintaining information about the review. The explainability module can use the HG model to explain a prediction generated by any model. We propose a path-restricted review-selection method biased by the user preference for item reviews and propose a novel explanation method based on a review graph. Experiments on real-world datasets confirm the ability of the HG model to capture appropriate explanations.
format text
author JENDAL, Theis E.
LE, Trung Hoang
LAUW, Hady Wirawan
LISSANDRINI, Matteo
DOLOG, Peter
HOSE, Katja
author_facet JENDAL, Theis E.
LE, Trung Hoang
LAUW, Hady Wirawan
LISSANDRINI, Matteo
DOLOG, Peter
HOSE, Katja
author_sort JENDAL, Theis E.
title Hypergraphs with attention on reviews for explainable recommendation
title_short Hypergraphs with attention on reviews for explainable recommendation
title_full Hypergraphs with attention on reviews for explainable recommendation
title_fullStr Hypergraphs with attention on reviews for explainable recommendation
title_full_unstemmed Hypergraphs with attention on reviews for explainable recommendation
title_sort hypergraphs with attention on reviews for explainable recommendation
publisher Institutional Knowledge at Singapore Management University
publishDate 2024
url https://ink.library.smu.edu.sg/sis_research/8724
https://ink.library.smu.edu.sg/context/sis_research/article/9727/viewcontent/ecir24.pdf
_version_ 1814047945329213440