Synthesizing aspect-driven recommendation explanations from reviews
Explanations help to make sense of recommendations, increasing the likelihood of adoption. However, existing approaches to explainable recommendations tend to rely on rigid, standardized templates, customized only via fill-in-the-blank aspect sentiments. For more flexible, literate, and varied expla...
Saved in:
Main Authors: | , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2020
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/5954 https://ink.library.smu.edu.sg/context/sis_research/article/6957/viewcontent/0336.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-6957 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-69572021-06-09T00:55:11Z Synthesizing aspect-driven recommendation explanations from reviews LE, Trung-Hoang LAUW, Hady W. Explanations help to make sense of recommendations, increasing the likelihood of adoption. However, existing approaches to explainable recommendations tend to rely on rigid, standardized templates, customized only via fill-in-the-blank aspect sentiments. For more flexible, literate, and varied explanations covering various aspects of interest, we synthesize an explanation by selecting snippets from reviews, while optimizing for representativeness and coherence. To fit target users' aspect preferences, we contextualize the opinions based on a compatible explainable recommendation model. Experiments on datasets of several product categories showcase the efficacies of our method as compared to baselines based on templates, review summarization, selection, and text generation. 2020-01-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/5954 info:doi/10.24963/ijcai.2020/336 https://ink.library.smu.edu.sg/context/sis_research/article/6957/viewcontent/0336.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 Contextualize Product categories Text generations Via fill Databases and Information Systems Data Science |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Contextualize Product categories Text generations Via fill Databases and Information Systems Data Science |
spellingShingle |
Contextualize Product categories Text generations Via fill Databases and Information Systems Data Science LE, Trung-Hoang LAUW, Hady W. Synthesizing aspect-driven recommendation explanations from reviews |
description |
Explanations help to make sense of recommendations, increasing the likelihood of adoption. However, existing approaches to explainable recommendations tend to rely on rigid, standardized templates, customized only via fill-in-the-blank aspect sentiments. For more flexible, literate, and varied explanations covering various aspects of interest, we synthesize an explanation by selecting snippets from reviews, while optimizing for representativeness and coherence. To fit target users' aspect preferences, we contextualize the opinions based on a compatible explainable recommendation model. Experiments on datasets of several product categories showcase the efficacies of our method as compared to baselines based on templates, review summarization, selection, and text generation. |
format |
text |
author |
LE, Trung-Hoang LAUW, Hady W. |
author_facet |
LE, Trung-Hoang LAUW, Hady W. |
author_sort |
LE, Trung-Hoang |
title |
Synthesizing aspect-driven recommendation explanations from reviews |
title_short |
Synthesizing aspect-driven recommendation explanations from reviews |
title_full |
Synthesizing aspect-driven recommendation explanations from reviews |
title_fullStr |
Synthesizing aspect-driven recommendation explanations from reviews |
title_full_unstemmed |
Synthesizing aspect-driven recommendation explanations from reviews |
title_sort |
synthesizing aspect-driven recommendation explanations from reviews |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2020 |
url |
https://ink.library.smu.edu.sg/sis_research/5954 https://ink.library.smu.edu.sg/context/sis_research/article/6957/viewcontent/0336.pdf |
_version_ |
1770575703233789952 |