Sentiment Analysis on Tweets about Diabetes: An Aspect-Level Approach

Handle URI:
http://hdl.handle.net/10754/622969
Title:
Sentiment Analysis on Tweets about Diabetes: An Aspect-Level Approach
Authors:
Salas-Zárate, María del Pilar ( 0000-0003-1818-3434 ) ; Medina-Moreira, José; Lagos-Ortiz, Katty ( 0000-0002-2510-7416 ) ; Luna-Aveiga, Harry; Rodriguez-Garcia, Miguel Angel ( 0000-0001-6244-6532 ) ; Valencia-García, Rafael ( 0000-0003-2457-1791 )
Abstract:
In recent years, some methods of sentiment analysis have been developed for the health domain; however, the diabetes domain has not been explored yet. In addition, there is a lack of approaches that analyze the positive or negative orientation of each aspect contained in a document (a review, a piece of news, and a tweet, among others). Based on this understanding, we propose an aspect-level sentiment analysis method based on ontologies in the diabetes domain. The sentiment of the aspects is calculated by considering the words around the aspect which are obtained through N-gram methods (N-gram after, N-gram before, and N-gram around). To evaluate the effectiveness of our method, we obtained a corpus from Twitter, which has been manually labelled at aspect level as positive, negative, or neutral. The experimental results show that the best result was obtained through the N-gram around method with a precision of 81.93%, a recall of 81.13%, and an -measure of 81.24%.
KAUST Department:
Computational Bioscience Research Center (CBRC)
Citation:
Salas-Zárate M del P, Medina-Moreira J, Lagos-Ortiz K, Luna-Aveiga H, Rodríguez-García MÁ, et al. (2017) Sentiment Analysis on Tweets about Diabetes: An Aspect-Level Approach. Computational and Mathematical Methods in Medicine 2017: 1–9. Available: http://dx.doi.org/10.1155/2017/5140631.
Publisher:
Hindawi Publishing Corporation
Journal:
Computational and Mathematical Methods in Medicine
Issue Date:
19-Feb-2017
DOI:
10.1155/2017/5140631
Type:
Article
ISSN:
1748-670X; 1748-6718
Sponsors:
This work has been funded by the Universidad de Guayaquil (Ecuador) through the project entitled “Tecnologías Inteligentes para la Autogestión de la Salud.” María del Pilar Salas-Zárate is supported by the National Council of Science and Technology (CONACYT), the Public Education Secretary (SEP), and the Mexican Government. Finally, this work has been also partially supported by the Spanish Ministry of Economy and Competitiveness and the European Commission (FEDER/ERDF) through project KBS4FIA (TIN2016-76323-R).
Additional Links:
https://www.hindawi.com/journals/cmmm/2017/5140631/
Appears in Collections:
Articles; Computational Bioscience Research Center (CBRC)

Full metadata record

DC FieldValue Language
dc.contributor.authorSalas-Zárate, María del Pilaren
dc.contributor.authorMedina-Moreira, Joséen
dc.contributor.authorLagos-Ortiz, Kattyen
dc.contributor.authorLuna-Aveiga, Harryen
dc.contributor.authorRodriguez-Garcia, Miguel Angelen
dc.contributor.authorValencia-García, Rafaelen
dc.date.accessioned2017-03-06T11:13:35Z-
dc.date.available2017-03-06T11:13:35Z-
dc.date.issued2017-02-19en
dc.identifier.citationSalas-Zárate M del P, Medina-Moreira J, Lagos-Ortiz K, Luna-Aveiga H, Rodríguez-García MÁ, et al. (2017) Sentiment Analysis on Tweets about Diabetes: An Aspect-Level Approach. Computational and Mathematical Methods in Medicine 2017: 1–9. Available: http://dx.doi.org/10.1155/2017/5140631.en
dc.identifier.issn1748-670Xen
dc.identifier.issn1748-6718en
dc.identifier.doi10.1155/2017/5140631en
dc.identifier.urihttp://hdl.handle.net/10754/622969-
dc.description.abstractIn recent years, some methods of sentiment analysis have been developed for the health domain; however, the diabetes domain has not been explored yet. In addition, there is a lack of approaches that analyze the positive or negative orientation of each aspect contained in a document (a review, a piece of news, and a tweet, among others). Based on this understanding, we propose an aspect-level sentiment analysis method based on ontologies in the diabetes domain. The sentiment of the aspects is calculated by considering the words around the aspect which are obtained through N-gram methods (N-gram after, N-gram before, and N-gram around). To evaluate the effectiveness of our method, we obtained a corpus from Twitter, which has been manually labelled at aspect level as positive, negative, or neutral. The experimental results show that the best result was obtained through the N-gram around method with a precision of 81.93%, a recall of 81.13%, and an -measure of 81.24%.en
dc.description.sponsorshipThis work has been funded by the Universidad de Guayaquil (Ecuador) through the project entitled “Tecnologías Inteligentes para la Autogestión de la Salud.” María del Pilar Salas-Zárate is supported by the National Council of Science and Technology (CONACYT), the Public Education Secretary (SEP), and the Mexican Government. Finally, this work has been also partially supported by the Spanish Ministry of Economy and Competitiveness and the European Commission (FEDER/ERDF) through project KBS4FIA (TIN2016-76323-R).en
dc.publisherHindawi Publishing Corporationen
dc.relation.urlhttps://www.hindawi.com/journals/cmmm/2017/5140631/en
dc.rightsThis is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.en
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.titleSentiment Analysis on Tweets about Diabetes: An Aspect-Level Approachen
dc.typeArticleen
dc.contributor.departmentComputational Bioscience Research Center (CBRC)en
dc.identifier.journalComputational and Mathematical Methods in Medicineen
dc.eprint.versionPublisher's Version/PDFen
dc.contributor.institutionDepartamento de Informática y Sistemas, Universidad de Murcia, 30100 Murcia, Spainen
dc.contributor.institutionUniversidad de Guayaquil, Cdla. Universitaria Salvador Allende, Guayaquil, Ecuadoren
kaust.authorRodriguez-Garcia, Miguel Angelen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.