A semi-supervised approach using label propagation to support citation screening

Citation screening, an integral process within systematic reviews that identifies citations relevant to the underlying research question, is a time-consuming and resource-intensive task. During the screening task, analysts manually assign a label to each citation, to designate whether a citation is...

ver descrição completa

Detalhes bibliográficos
Autores: Kontonatsios, Georgios, Brockmeier, Austin Jay, Przybyla, Piotr, McNaught, John, Mu, Tingting, Goulermas, John Y., Ananiadou, Sophia
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2017
País:España
Recursos:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:10230/72443
Acesso em linha:https://hdl.handle.net/10230/72443
http://dx.doi.org/10.1016/j.jbi.2017.06.018
http://hdl.handle.net/10230/72443
Access Level:acceso abierto
Palavra-chave:Active learning
Label propagation
Citation screening
Semi-supervised learning
Text classification
id ES_092e8a61e1b8799a3afa2943d50e0a2c
oai_identifier_str oai:recercat.cat:10230/72443
network_acronym_str ES
network_name_str España
repository_id_str
spelling A semi-supervised approach using label propagation to support citation screeningKontonatsios, GeorgiosBrockmeier, Austin JayPrzybyla, PiotrMcNaught, JohnMu, TingtingGoulermas, John Y.Ananiadou, SophiaActive learningLabel propagationCitation screeningSemi-supervised learningText classificationCitation screening, an integral process within systematic reviews that identifies citations relevant to the underlying research question, is a time-consuming and resource-intensive task. During the screening task, analysts manually assign a label to each citation, to designate whether a citation is eligible for inclusion in the review. Recently, several studies have explored the use of active learning in text classification to reduce the human workload involved in the screening task. However, existing approaches require a significant amount of manually labelled citations for the text classification to achieve a robust performance. In this paper, we propose a semi-supervised method that identifies relevant citations as early as possible in the screening process by exploiting the pairwise similarities between labelled and unlabelled citations to improve the classification performance without additional manual labelling effort. Our approach is based on the hypothesis that similar citations share the same label (e.g., if one citation should be included, then other similar citations should be included also). To calculate the similarity between labelled and unlabelled citations we investigate two different feature spaces, namely a bag-of-words and a spectral embedding based on the bag-of-words. The semi-supervised method propagates the classification codes of manually labelled citations to neighbouring unlabelled citations in the feature space. The automatically labelled citations are combined with the manually labelled citations to form an augmented training set. For evaluation purposes, we apply our method to reviews from clinical and public health. The results show that our semi-supervised method with label propagation achieves statistically significant improvements over two state-of-the-art active learning approaches across both clinical and public health reviews.Elsevier2026202620172026info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttps://hdl.handle.net/10230/72443http://dx.doi.org/10.1016/j.jbi.2017.06.018http://hdl.handle.net/10230/72443reponame:Recercat. Dipósit de la Recerca de Catalunyainstname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)InglésJournal of Biomedical Informatics. 2017 Aug;72:67-76© 2017 The Authors. Published by Elsevier Inc. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).http://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:recercat.cat:10230/724432026-05-29T05:05:01Z
dc.title.none.fl_str_mv A semi-supervised approach using label propagation to support citation screening
title A semi-supervised approach using label propagation to support citation screening
spellingShingle A semi-supervised approach using label propagation to support citation screening
Kontonatsios, Georgios
Active learning
Label propagation
Citation screening
Semi-supervised learning
Text classification
title_short A semi-supervised approach using label propagation to support citation screening
title_full A semi-supervised approach using label propagation to support citation screening
title_fullStr A semi-supervised approach using label propagation to support citation screening
title_full_unstemmed A semi-supervised approach using label propagation to support citation screening
title_sort A semi-supervised approach using label propagation to support citation screening
dc.creator.none.fl_str_mv Kontonatsios, Georgios
Brockmeier, Austin Jay
Przybyla, Piotr
McNaught, John
Mu, Tingting
Goulermas, John Y.
Ananiadou, Sophia
author Kontonatsios, Georgios
author_facet Kontonatsios, Georgios
Brockmeier, Austin Jay
Przybyla, Piotr
McNaught, John
Mu, Tingting
Goulermas, John Y.
Ananiadou, Sophia
author_role author
author2 Brockmeier, Austin Jay
Przybyla, Piotr
McNaught, John
Mu, Tingting
Goulermas, John Y.
Ananiadou, Sophia
author2_role author
author
author
author
author
author
dc.subject.none.fl_str_mv Active learning
Label propagation
Citation screening
Semi-supervised learning
Text classification
topic Active learning
Label propagation
Citation screening
Semi-supervised learning
Text classification
description Citation screening, an integral process within systematic reviews that identifies citations relevant to the underlying research question, is a time-consuming and resource-intensive task. During the screening task, analysts manually assign a label to each citation, to designate whether a citation is eligible for inclusion in the review. Recently, several studies have explored the use of active learning in text classification to reduce the human workload involved in the screening task. However, existing approaches require a significant amount of manually labelled citations for the text classification to achieve a robust performance. In this paper, we propose a semi-supervised method that identifies relevant citations as early as possible in the screening process by exploiting the pairwise similarities between labelled and unlabelled citations to improve the classification performance without additional manual labelling effort. Our approach is based on the hypothesis that similar citations share the same label (e.g., if one citation should be included, then other similar citations should be included also). To calculate the similarity between labelled and unlabelled citations we investigate two different feature spaces, namely a bag-of-words and a spectral embedding based on the bag-of-words. The semi-supervised method propagates the classification codes of manually labelled citations to neighbouring unlabelled citations in the feature space. The automatically labelled citations are combined with the manually labelled citations to form an augmented training set. For evaluation purposes, we apply our method to reviews from clinical and public health. The results show that our semi-supervised method with label propagation achieves statistically significant improvements over two state-of-the-art active learning approaches across both clinical and public health reviews.
publishDate 2017
dc.date.none.fl_str_mv 2017
2026
2026
2026
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/10230/72443
http://dx.doi.org/10.1016/j.jbi.2017.06.018
http://hdl.handle.net/10230/72443
url https://hdl.handle.net/10230/72443
http://dx.doi.org/10.1016/j.jbi.2017.06.018
http://hdl.handle.net/10230/72443
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Journal of Biomedical Informatics. 2017 Aug;72:67-76
dc.rights.none.fl_str_mv http://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:Recercat. Dipósit de la Recerca de Catalunya
instname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
instname_str Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
reponame_str Recercat. Dipósit de la Recerca de Catalunya
collection Recercat. Dipósit de la Recerca de Catalunya
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869403091175997440
score 15,812429