A Multi-Channel Convolutional Neural Network approach to automate the citation screening process

<p dir="ltr">The systematic literature review (SLR) process is separated into several steps to increase rigor and reproducibility. The selection of primary studies (i.e., citation screening) is an important step in the SLR process. The citation screening process aims to identify the...

Full description

Saved in:
Bibliographic Details
Main Author: Raymon van Dinter (10521952) (author)
Other Authors: Cagatay Catal (6897842) (author), Bedir Tekinerdogan (6897839) (author)
Published: 2021
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513547795431424
author Raymon van Dinter (10521952)
author2 Cagatay Catal (6897842)
Bedir Tekinerdogan (6897839)
author2_role author
author
author_facet Raymon van Dinter (10521952)
Cagatay Catal (6897842)
Bedir Tekinerdogan (6897839)
author_role author
dc.creator.none.fl_str_mv Raymon van Dinter (10521952)
Cagatay Catal (6897842)
Bedir Tekinerdogan (6897839)
dc.date.none.fl_str_mv 2021-11-01T00:00:00Z
dc.identifier.none.fl_str_mv 10.1016/j.asoc.2021.107765
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/A_Multi-Channel_Convolutional_Neural_Network_approach_to_automate_the_citation_screening_process/24420484
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Computer vision and multimedia computation
Machine learning
Language, communication and culture
Linguistics
Systematic literature review (SLR)
Citation screening
Automation
Neural networks
Natural language processing
dc.title.none.fl_str_mv A Multi-Channel Convolutional Neural Network approach to automate the citation screening process
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">The systematic literature review (SLR) process is separated into several steps to increase rigor and reproducibility. The selection of primary studies (i.e., citation screening) is an important step in the SLR process. The citation screening process aims to identify the relevant primary studies fairly and with high rigor using selection criteria. Through the study selection criteria, reviewers determine whether an article should be included or excluded from the SLR. However, the screening process is highly time-consuming and error-prone as the researchers must read each title and possibly hundreds to thousands of abstracts and full-text documents. This study aims to automate the citation screening process using Deep Learning algorithms. With this, it is aimed to reduce the time and costs of the citation screening process and increase the precision and recall of the relevant primary studies. A Multi-Channel Convolutional Neural Network (CNN) is proposed, which can automatically classify a given set of citations. As the architecture uses the title and abstract as features, our end-to-end pipeline is domain-independent. We have performed six experiments to assess the performance of Multi-Channel CNNs across 20 publicly available systematic literature review datasets. It was shown that for 18 out of 20 review datasets, the proposed method achieved significant workload savings of at least 10%, while in several cases, our model yielded a statistically significantly better performance over two benchmark review datasets. We conclude that Multi-Channel CNNs are effective for the citation screening process in SLRs. Multi-Channel CNNs perform best on large datasets of over 2500 samples with few abstracts missing.</p><h2>Other Information</h2><p dir="ltr">Published in: Applied Soft Computing<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.asoc.2021.107765" target="_blank">https://dx.doi.org/10.1016/j.asoc.2021.107765</a></p>
eu_rights_str_mv openAccess
id Manara2_85efd09d12da001a53807fd946ff8cd5
identifier_str_mv 10.1016/j.asoc.2021.107765
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24420484
publishDate 2021
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling A Multi-Channel Convolutional Neural Network approach to automate the citation screening processRaymon van Dinter (10521952)Cagatay Catal (6897842)Bedir Tekinerdogan (6897839)Information and computing sciencesComputer vision and multimedia computationMachine learningLanguage, communication and cultureLinguisticsSystematic literature review (SLR)Citation screeningAutomationNeural networksNatural language processing<p dir="ltr">The systematic literature review (SLR) process is separated into several steps to increase rigor and reproducibility. The selection of primary studies (i.e., citation screening) is an important step in the SLR process. The citation screening process aims to identify the relevant primary studies fairly and with high rigor using selection criteria. Through the study selection criteria, reviewers determine whether an article should be included or excluded from the SLR. However, the screening process is highly time-consuming and error-prone as the researchers must read each title and possibly hundreds to thousands of abstracts and full-text documents. This study aims to automate the citation screening process using Deep Learning algorithms. With this, it is aimed to reduce the time and costs of the citation screening process and increase the precision and recall of the relevant primary studies. A Multi-Channel Convolutional Neural Network (CNN) is proposed, which can automatically classify a given set of citations. As the architecture uses the title and abstract as features, our end-to-end pipeline is domain-independent. We have performed six experiments to assess the performance of Multi-Channel CNNs across 20 publicly available systematic literature review datasets. It was shown that for 18 out of 20 review datasets, the proposed method achieved significant workload savings of at least 10%, while in several cases, our model yielded a statistically significantly better performance over two benchmark review datasets. We conclude that Multi-Channel CNNs are effective for the citation screening process in SLRs. Multi-Channel CNNs perform best on large datasets of over 2500 samples with few abstracts missing.</p><h2>Other Information</h2><p dir="ltr">Published in: Applied Soft Computing<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.asoc.2021.107765" target="_blank">https://dx.doi.org/10.1016/j.asoc.2021.107765</a></p>2021-11-01T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.asoc.2021.107765https://figshare.com/articles/journal_contribution/A_Multi-Channel_Convolutional_Neural_Network_approach_to_automate_the_citation_screening_process/24420484CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/244204842021-11-01T00:00:00Z
spellingShingle A Multi-Channel Convolutional Neural Network approach to automate the citation screening process
Raymon van Dinter (10521952)
Information and computing sciences
Computer vision and multimedia computation
Machine learning
Language, communication and culture
Linguistics
Systematic literature review (SLR)
Citation screening
Automation
Neural networks
Natural language processing
status_str publishedVersion
title A Multi-Channel Convolutional Neural Network approach to automate the citation screening process
title_full A Multi-Channel Convolutional Neural Network approach to automate the citation screening process
title_fullStr A Multi-Channel Convolutional Neural Network approach to automate the citation screening process
title_full_unstemmed A Multi-Channel Convolutional Neural Network approach to automate the citation screening process
title_short A Multi-Channel Convolutional Neural Network approach to automate the citation screening process
title_sort A Multi-Channel Convolutional Neural Network approach to automate the citation screening process
topic Information and computing sciences
Computer vision and multimedia computation
Machine learning
Language, communication and culture
Linguistics
Systematic literature review (SLR)
Citation screening
Automation
Neural networks
Natural language processing