Sentiment classification of time-sync comments: A semi-supervised hierarchical deep learning method

Gao, Renzhi; Yao, Xiaoyu; Wang, Zhao; Abedin, Mohammad

doi:10.1016/j.ejor.2023.11.035

Journal article 232 views 143 downloads

Sentiment classification of time-sync comments: A semi-supervised hierarchical deep learning method

Renzhi Gao, Xiaoyu Yao, Zhao Wang, Mohammad Abedin

European Journal of Operational Research, Volume: 314, Issue: 3, Pages: 1159 - 1173

Swansea University Author: Mohammad Abedin

PDF | Accepted Manuscript

Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention).
Download (1.2MB)

Check full text

DOI (Published version): 10.1016/j.ejor.2023.11.035

Abstract

Time-sync comment (TSC) has emerged as a new type of textual comment for real-time user interactions on online video platforms. The sentiment classification of TSCs provides considerable potential for platforms to optimize operation strategies but inevitably faces great challenges due to the TSCs’ o...

Full description

Published in:	European Journal of Operational Research
ISSN:	0377-2217
Published:	Elsevier BV 2024
Online Access:	Check full text
URI:	https://cronfa.swan.ac.uk/Record/cronfa65091
Tags:	Add Tag No Tags, Be the first to tag this record!

first_indexed	2023-11-24T11:49:29Z
last_indexed	2023-11-24T11:49:29Z
id	cronfa65091
recordtype	SURis
fullrecord	<?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>65091</id><entry>2023-11-24</entry><title>Sentiment classification of time-sync comments: A semi-supervised hierarchical deep learning method</title><swanseaauthors><author><sid>4ed8c020eae0c9bec4f5d9495d86d415</sid><firstname>Mohammad</firstname><surname>Abedin</surname><name>Mohammad Abedin</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2023-11-24</date><deptcode>BAF</deptcode><abstract>Time-sync comment (TSC) has emerged as a new type of textual comment for real-time user interactions on online video platforms. The sentiment classification of TSCs provides considerable potential for platforms to optimize operation strategies but inevitably faces great challenges due to the TSCs’ often uninformative and informal text. Considering the contextual dependency among TSCs posted within the same video clip, this study posits that contextual TSCs may benefit the sentiment classification of a target TSC. To address the challenges of leveraging contextual TSCs, such as their semantic representation and fusion, we propose a semi-supervised hierarchical deep learning method for the sentiment classification of TSCs. We design a hierarchical architecture to capture the semantics of TSCs at the word, comment, and context levels. Considering the varying importance of words and comments, we also design attention mechanisms to focus on important sentiment information and fuse semantic representations. Empirical evaluation shows that the proposed method outperforms benchmarked sentiment classification methods. This study advances our knowledge of contextual information indicative of TSC sentiment, and contributes to improving the service operation of online video platforms.</abstract><type>Journal Article</type><journal>European Journal of Operational Research</journal><volume>314</volume><journalNumber>3</journalNumber><paginationStart>1159</paginationStart><paginationEnd>1173</paginationEnd><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0377-2217</issnPrint><issnElectronic/><keywords>OR in marketing; Time-sync comment; Sentiment classification; Contextual dependency; Semi-supervised deep learning</keywords><publishedDay>1</publishedDay><publishedMonth>5</publishedMonth><publishedYear>2024</publishedYear><publishedDate>2024-05-01</publishedDate><doi>10.1016/j.ejor.2023.11.035</doi><url/><notes/><college>COLLEGE NANME</college><department>Accounting and Finance</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>BAF</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>This work was supported by the National Natural Science Foundation of China [Grant 72101073], the Natural Science Foundation of Anhui Province [Grant 2108085MG234], and the Fundamental Research Funds for the Central Universities [Grant JZ2023YQTD0075].</funders><projectreference/><lastEdited>2024-03-07T15:43:04.1749242</lastEdited><Created>2023-11-24T11:48:43.0433727</Created><path><level id="1">Faculty of Humanities and Social Sciences</level><level id="2">School of Management - Accounting and Finance</level></path><authors><author><firstname>Renzhi</firstname><surname>Gao</surname><order>1</order></author><author><firstname>Xiaoyu</firstname><surname>Yao</surname><order>2</order></author><author><firstname>Zhao</firstname><surname>Wang</surname><order>3</order></author><author><firstname>Mohammad</firstname><surname>Abedin</surname><order>4</order></author></authors><documents><document><filename>65091__29437__96e04f23e56744c589e2405093337628.pdf</filename><originalFilename>65091.AAM.pdf</originalFilename><uploaded>2024-01-12T14:26:07.3216380</uploaded><type>Output</type><contentLength>1259517</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><documentNotes>Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling	v2 65091 2023-11-24 Sentiment classification of time-sync comments: A semi-supervised hierarchical deep learning method 4ed8c020eae0c9bec4f5d9495d86d415 Mohammad Abedin Mohammad Abedin true false 2023-11-24 BAF Time-sync comment (TSC) has emerged as a new type of textual comment for real-time user interactions on online video platforms. The sentiment classification of TSCs provides considerable potential for platforms to optimize operation strategies but inevitably faces great challenges due to the TSCs’ often uninformative and informal text. Considering the contextual dependency among TSCs posted within the same video clip, this study posits that contextual TSCs may benefit the sentiment classification of a target TSC. To address the challenges of leveraging contextual TSCs, such as their semantic representation and fusion, we propose a semi-supervised hierarchical deep learning method for the sentiment classification of TSCs. We design a hierarchical architecture to capture the semantics of TSCs at the word, comment, and context levels. Considering the varying importance of words and comments, we also design attention mechanisms to focus on important sentiment information and fuse semantic representations. Empirical evaluation shows that the proposed method outperforms benchmarked sentiment classification methods. This study advances our knowledge of contextual information indicative of TSC sentiment, and contributes to improving the service operation of online video platforms. Journal Article European Journal of Operational Research 314 3 1159 1173 Elsevier BV 0377-2217 OR in marketing; Time-sync comment; Sentiment classification; Contextual dependency; Semi-supervised deep learning 1 5 2024 2024-05-01 10.1016/j.ejor.2023.11.035 COLLEGE NANME Accounting and Finance COLLEGE CODE BAF Swansea University This work was supported by the National Natural Science Foundation of China [Grant 72101073], the Natural Science Foundation of Anhui Province [Grant 2108085MG234], and the Fundamental Research Funds for the Central Universities [Grant JZ2023YQTD0075]. 2024-03-07T15:43:04.1749242 2023-11-24T11:48:43.0433727 Faculty of Humanities and Social Sciences School of Management - Accounting and Finance Renzhi Gao 1 Xiaoyu Yao 2 Zhao Wang 3 Mohammad Abedin 4 65091__29437__96e04f23e56744c589e2405093337628.pdf 65091.AAM.pdf 2024-01-12T14:26:07.3216380 Output 1259517 application/pdf Accepted Manuscript true Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention). true eng https://creativecommons.org/licenses/by/4.0/
title	Sentiment classification of time-sync comments: A semi-supervised hierarchical deep learning method
spellingShingle	Sentiment classification of time-sync comments: A semi-supervised hierarchical deep learning method Mohammad Abedin
title_short	Sentiment classification of time-sync comments: A semi-supervised hierarchical deep learning method
title_full	Sentiment classification of time-sync comments: A semi-supervised hierarchical deep learning method
title_fullStr	Sentiment classification of time-sync comments: A semi-supervised hierarchical deep learning method
title_full_unstemmed	Sentiment classification of time-sync comments: A semi-supervised hierarchical deep learning method
title_sort	Sentiment classification of time-sync comments: A semi-supervised hierarchical deep learning method
author_id_str_mv	4ed8c020eae0c9bec4f5d9495d86d415
author_id_fullname_str_mv	4ed8c020eae0c9bec4f5d9495d86d415_***_Mohammad Abedin
author	Mohammad Abedin
author2	Renzhi Gao Xiaoyu Yao Zhao Wang Mohammad Abedin
format	Journal article
container_title	European Journal of Operational Research
container_volume	314
container_issue	3
container_start_page	1159
publishDate	2024
institution	Swansea University
issn	0377-2217
doi_str_mv	10.1016/j.ejor.2023.11.035
publisher	Elsevier BV
college_str	Faculty of Humanities and Social Sciences
hierarchytype
hierarchy_top_id	facultyofhumanitiesandsocialsciences
hierarchy_top_title	Faculty of Humanities and Social Sciences
hierarchy_parent_id	facultyofhumanitiesandsocialsciences
hierarchy_parent_title	Faculty of Humanities and Social Sciences
department_str	School of Management - Accounting and Finance{{{_:::_}}}Faculty of Humanities and Social Sciences{{{_:::_}}}School of Management - Accounting and Finance
document_store_str	1
active_str	0
description	Time-sync comment (TSC) has emerged as a new type of textual comment for real-time user interactions on online video platforms. The sentiment classification of TSCs provides considerable potential for platforms to optimize operation strategies but inevitably faces great challenges due to the TSCs’ often uninformative and informal text. Considering the contextual dependency among TSCs posted within the same video clip, this study posits that contextual TSCs may benefit the sentiment classification of a target TSC. To address the challenges of leveraging contextual TSCs, such as their semantic representation and fusion, we propose a semi-supervised hierarchical deep learning method for the sentiment classification of TSCs. We design a hierarchical architecture to capture the semantics of TSCs at the word, comment, and context levels. Considering the varying importance of words and comments, we also design attention mechanisms to focus on important sentiment information and fuse semantic representations. Empirical evaluation shows that the proposed method outperforms benchmarked sentiment classification methods. This study advances our knowledge of contextual information indicative of TSC sentiment, and contributes to improving the service operation of online video platforms.
published_date	2024-05-01T15:43:01Z
_version_	1792882697731833856
score	11.037319

Sentiment classification of time-sync comments: A semi-supervised hierarchical deep learning method

Similar Items