Review Helpfulness Assessment based on Convolutional Neural Network

In this paper we describe the implementation of a convolutional neural network (CNN) used to assess online review helpfulness. To our knowledge, this is the first use of this architecture to address this problem. We explore the impact of two related factors impacting CNN performance: different word...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Qu, Xianshan, Li, Xiaopeng, Rose, John R
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Qu, Xianshan
Li, Xiaopeng
Rose, John R
description In this paper we describe the implementation of a convolutional neural network (CNN) used to assess online review helpfulness. To our knowledge, this is the first use of this architecture to address this problem. We explore the impact of two related factors impacting CNN performance: different word embedding initializations and different input review lengths. We also propose an approach to combining rating star information with review text to further improve prediction accuracy. We demonstrate that this can improve the overall accuracy by 2%. Finally, we evaluate the method on a benchmark dataset and show an improvement in accuracy relative to published results for traditional methods of 2.5% for a model trained using only review text and 4.24% for a model trained on a combination of rating star information and review text.
doi_str_mv 10.48550/arxiv.1808.09016
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1808_09016</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1808_09016</sourcerecordid><originalsourceid>FETCH-LOGICAL-a676-f2eb52e2f89eda57636fc93a69b5b291e94c9d083ed87e8e6dfc8d6ef05aa0343</originalsourceid><addsrcrecordid>eNotz0FLwzAYgOFcdpBtP8CT-QOtadOkyXEU3YShILuXr80XKGbJSNrO_ftp9fTcXngJeSxYXikh2DPE72HOC8VUzjQr5ANpPnEe8EoP6C52ch5ToruUfjijH2kHCQ0NnjbBz8FN4xA8OPqOU1wYryF-bcjKgku4_XdNTq8vp-aQHT_2b83umIGsZWZL7ESJpVUaDYhacml7zUHqTnSlLlBXvTZMcTSqRoXS2F4ZiZYJAMYrviZPf9nlor3E4Qzx1v7etMsNvwOlTkZP</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Review Helpfulness Assessment based on Convolutional Neural Network</title><source>arXiv.org</source><creator>Qu, Xianshan ; Li, Xiaopeng ; Rose, John R</creator><creatorcontrib>Qu, Xianshan ; Li, Xiaopeng ; Rose, John R</creatorcontrib><description>In this paper we describe the implementation of a convolutional neural network (CNN) used to assess online review helpfulness. To our knowledge, this is the first use of this architecture to address this problem. We explore the impact of two related factors impacting CNN performance: different word embedding initializations and different input review lengths. We also propose an approach to combining rating star information with review text to further improve prediction accuracy. We demonstrate that this can improve the overall accuracy by 2%. Finally, we evaluate the method on a benchmark dataset and show an improvement in accuracy relative to published results for traditional methods of 2.5% for a model trained using only review text and 4.24% for a model trained on a combination of rating star information and review text.</description><identifier>DOI: 10.48550/arxiv.1808.09016</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2018-08</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1808.09016$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1808.09016$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Qu, Xianshan</creatorcontrib><creatorcontrib>Li, Xiaopeng</creatorcontrib><creatorcontrib>Rose, John R</creatorcontrib><title>Review Helpfulness Assessment based on Convolutional Neural Network</title><description>In this paper we describe the implementation of a convolutional neural network (CNN) used to assess online review helpfulness. To our knowledge, this is the first use of this architecture to address this problem. We explore the impact of two related factors impacting CNN performance: different word embedding initializations and different input review lengths. We also propose an approach to combining rating star information with review text to further improve prediction accuracy. We demonstrate that this can improve the overall accuracy by 2%. Finally, we evaluate the method on a benchmark dataset and show an improvement in accuracy relative to published results for traditional methods of 2.5% for a model trained using only review text and 4.24% for a model trained on a combination of rating star information and review text.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz0FLwzAYgOFcdpBtP8CT-QOtadOkyXEU3YShILuXr80XKGbJSNrO_ftp9fTcXngJeSxYXikh2DPE72HOC8VUzjQr5ANpPnEe8EoP6C52ch5ToruUfjijH2kHCQ0NnjbBz8FN4xA8OPqOU1wYryF-bcjKgku4_XdNTq8vp-aQHT_2b83umIGsZWZL7ESJpVUaDYhacml7zUHqTnSlLlBXvTZMcTSqRoXS2F4ZiZYJAMYrviZPf9nlor3E4Qzx1v7etMsNvwOlTkZP</recordid><startdate>20180827</startdate><enddate>20180827</enddate><creator>Qu, Xianshan</creator><creator>Li, Xiaopeng</creator><creator>Rose, John R</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20180827</creationdate><title>Review Helpfulness Assessment based on Convolutional Neural Network</title><author>Qu, Xianshan ; Li, Xiaopeng ; Rose, John R</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a676-f2eb52e2f89eda57636fc93a69b5b291e94c9d083ed87e8e6dfc8d6ef05aa0343</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Qu, Xianshan</creatorcontrib><creatorcontrib>Li, Xiaopeng</creatorcontrib><creatorcontrib>Rose, John R</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Qu, Xianshan</au><au>Li, Xiaopeng</au><au>Rose, John R</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Review Helpfulness Assessment based on Convolutional Neural Network</atitle><date>2018-08-27</date><risdate>2018</risdate><abstract>In this paper we describe the implementation of a convolutional neural network (CNN) used to assess online review helpfulness. To our knowledge, this is the first use of this architecture to address this problem. We explore the impact of two related factors impacting CNN performance: different word embedding initializations and different input review lengths. We also propose an approach to combining rating star information with review text to further improve prediction accuracy. We demonstrate that this can improve the overall accuracy by 2%. Finally, we evaluate the method on a benchmark dataset and show an improvement in accuracy relative to published results for traditional methods of 2.5% for a model trained using only review text and 4.24% for a model trained on a combination of rating star information and review text.</abstract><doi>10.48550/arxiv.1808.09016</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.1808.09016
ispartof
issn
language eng
recordid cdi_arxiv_primary_1808_09016
source arXiv.org
subjects Computer Science - Artificial Intelligence
Computer Science - Computer Vision and Pattern Recognition
title Review Helpfulness Assessment based on Convolutional Neural Network
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-05T22%3A26%3A19IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Review%20Helpfulness%20Assessment%20based%20on%20Convolutional%20Neural%20Network&rft.au=Qu,%20Xianshan&rft.date=2018-08-27&rft_id=info:doi/10.48550/arxiv.1808.09016&rft_dat=%3Carxiv_GOX%3E1808_09016%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true