On the Use of Opinionated Explanations to Rank and Justify Recommendations

Files in This Item:
 File SizeFormat
Downloadinsight_publication.pdf1.66 MBAdobe PDF
Title: On the Use of Opinionated Explanations to Rank and Justify Recommendations
Authors: Muhammad, KhalilLawlor, AonghusSmyth, Barry
Permanent link: http://hdl.handle.net/10197/9032
Date: 18-May-2016
Online since: 2017-11-06T18:18:44Z
Abstract: Explanations are an important part of modern recommendersystems. They help users to make better decisions, improvethe conversion rate of browsers into buyers, and lead togreater user satisfaction in the long-run. In this paper, we extendrecent work on generating explanations by mining userreviews. We show how this leads to a novel explanation formatthat can be tailored for the needs of the individual user.Moreover, we demonstrate how the explanations themselvescan be used to rank recommendations so that items which canbe associated with a more compelling explanation are rankedahead of items that have a less compelling explanation. Weevaluate our approach using a large-scale, real-world TripAdvisordataset.
Funding Details: Science Foundation Ireland
Type of material: Conference Publication
Publisher: Association for the Advancement of Artificial Intelligence
Copyright (published version): 2016 Association for the Advancement of Artificial Intelligence
Keywords: Recommender SystemsExplanationsOpinion miningSentiment analysis
Other versions: http://www.aaai.org/ocs/index.php/FLAIRS/FLAIRS16/paper/view/12921
Language: en
Status of Item: Peer reviewed
Conference Details: FLAIRS 2016, the 29th International Florida Artificial Intelligence Research Society Conference, Key Largo, Florida
This item is made available under a Creative Commons License: https://creativecommons.org/licenses/by-nc-nd/3.0/ie/
Appears in Collections:Insight Research Collection

Show full item record

Page view(s)

678
Last Week
2
Last month
checked on Sep 22, 2021

Download(s)

90
checked on Sep 22, 2021

Google ScholarTM

Check


If you are a publisher or author and have copyright concerns for any item, please email research.repository@ucd.ie and the item will be withdrawn immediately. The author or person responsible for depositing the article will be contacted within one business day.