A Knowledge-Based Recommendation System That Includes Sentiment Analysis and Deep Learning
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1109/TII.2018.2867174 http://hdl.handle.net/11449/186268 |
Resumo: | Online social networks provide relevant information on users' opinion about different themes. Thus, applications, such as monitoring and recommendation systems (RS) can collect and analyze this data. This paper presents a knowledge-based recommendation system (KBRS), which includes an emotional health monitoring system to detect users with potential psychological disturbances, specifically, depression and stress. Depending on the monitoring results, the KBRS, based on ontologies and sentiment analysis, is activated to send happy, calm, relaxing, or motivational messages to users with psychological disturbances. Also, the solution includes a mechanism to send warning messages to authorized persons, in case a depression disturbance is detected by the monitoring system. The detection of sentences with depressive and stressful content is performed through a convolutional neural network and a bidirectional long short-term memory recurrent neural networks (RNN); the proposed method reached an accuracy of 0.89 and 0.90 to detect depressed and stressed users, respectively. Experimental results show that the proposed KBRS reached a rating of 94% of very satisfied users, as opposed to 69% reached by a RS without the use of neither a sentiment metric nor ontologies. Additionally, subjective test results demonstrated that the proposed solution consumes low memory, processing, and energy from current mobile electronic devices. |
id |
UNSP_2f9a923d618acd431f0cc6f6d8b8d456 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/186268 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
A Knowledge-Based Recommendation System That Includes Sentiment Analysis and Deep LearningDeep learningknowledge personalization and customizationrecommendation systemsentiment analysissocial networksOnline social networks provide relevant information on users' opinion about different themes. Thus, applications, such as monitoring and recommendation systems (RS) can collect and analyze this data. This paper presents a knowledge-based recommendation system (KBRS), which includes an emotional health monitoring system to detect users with potential psychological disturbances, specifically, depression and stress. Depending on the monitoring results, the KBRS, based on ontologies and sentiment analysis, is activated to send happy, calm, relaxing, or motivational messages to users with psychological disturbances. Also, the solution includes a mechanism to send warning messages to authorized persons, in case a depression disturbance is detected by the monitoring system. The detection of sentences with depressive and stressful content is performed through a convolutional neural network and a bidirectional long short-term memory recurrent neural networks (RNN); the proposed method reached an accuracy of 0.89 and 0.90 to detect depressed and stressed users, respectively. Experimental results show that the proposed KBRS reached a rating of 94% of very satisfied users, as opposed to 69% reached by a RS without the use of neither a sentiment metric nor ontologies. Additionally, subjective test results demonstrated that the proposed solution consumes low memory, processing, and energy from current mobile electronic devices.Univ Fed Lavras, BR-37200000 Lavras, MG, BrazilUniv Estadual Paulista, Biosci Inst Rio Claro, BR-13506900 Sao Paulo, BrazilUniv Sao Paulo, Polytech Sch, BR-05508010 Sao Paulo, BrazilUniv Estadual Paulista, Biosci Inst Rio Claro, BR-13506900 Sao Paulo, BrazilIeee-inst Electrical Electronics Engineers IncUniversidade Federal de Lavras (UFLA)Universidade Estadual Paulista (Unesp)Universidade de São Paulo (USP)Rosa, Renata LopesSchwartz, Gisele Maria [UNESP]Ruggiero, Wilson VicenteRodrigue, Derndstenes Zegarra2019-10-04T15:23:58Z2019-10-04T15:23:58Z2019-04-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article2124-2135http://dx.doi.org/10.1109/TII.2018.2867174Ieee Transactions On Industrial Informatics. Piscataway: Ieee-inst Electrical Electronics Engineers Inc, v. 15, n. 4, p. 2124-2135, 2019.1551-3203http://hdl.handle.net/11449/18626810.1109/TII.2018.2867174WOS:000467095500027Web of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengIeee Transactions On Industrial Informaticsinfo:eu-repo/semantics/openAccess2021-10-23T00:57:11Zoai:repositorio.unesp.br:11449/186268Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462021-10-23T00:57:11Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
A Knowledge-Based Recommendation System That Includes Sentiment Analysis and Deep Learning |
title |
A Knowledge-Based Recommendation System That Includes Sentiment Analysis and Deep Learning |
spellingShingle |
A Knowledge-Based Recommendation System That Includes Sentiment Analysis and Deep Learning Rosa, Renata Lopes Deep learning knowledge personalization and customization recommendation system sentiment analysis social networks |
title_short |
A Knowledge-Based Recommendation System That Includes Sentiment Analysis and Deep Learning |
title_full |
A Knowledge-Based Recommendation System That Includes Sentiment Analysis and Deep Learning |
title_fullStr |
A Knowledge-Based Recommendation System That Includes Sentiment Analysis and Deep Learning |
title_full_unstemmed |
A Knowledge-Based Recommendation System That Includes Sentiment Analysis and Deep Learning |
title_sort |
A Knowledge-Based Recommendation System That Includes Sentiment Analysis and Deep Learning |
author |
Rosa, Renata Lopes |
author_facet |
Rosa, Renata Lopes Schwartz, Gisele Maria [UNESP] Ruggiero, Wilson Vicente Rodrigue, Derndstenes Zegarra |
author_role |
author |
author2 |
Schwartz, Gisele Maria [UNESP] Ruggiero, Wilson Vicente Rodrigue, Derndstenes Zegarra |
author2_role |
author author author |
dc.contributor.none.fl_str_mv |
Universidade Federal de Lavras (UFLA) Universidade Estadual Paulista (Unesp) Universidade de São Paulo (USP) |
dc.contributor.author.fl_str_mv |
Rosa, Renata Lopes Schwartz, Gisele Maria [UNESP] Ruggiero, Wilson Vicente Rodrigue, Derndstenes Zegarra |
dc.subject.por.fl_str_mv |
Deep learning knowledge personalization and customization recommendation system sentiment analysis social networks |
topic |
Deep learning knowledge personalization and customization recommendation system sentiment analysis social networks |
description |
Online social networks provide relevant information on users' opinion about different themes. Thus, applications, such as monitoring and recommendation systems (RS) can collect and analyze this data. This paper presents a knowledge-based recommendation system (KBRS), which includes an emotional health monitoring system to detect users with potential psychological disturbances, specifically, depression and stress. Depending on the monitoring results, the KBRS, based on ontologies and sentiment analysis, is activated to send happy, calm, relaxing, or motivational messages to users with psychological disturbances. Also, the solution includes a mechanism to send warning messages to authorized persons, in case a depression disturbance is detected by the monitoring system. The detection of sentences with depressive and stressful content is performed through a convolutional neural network and a bidirectional long short-term memory recurrent neural networks (RNN); the proposed method reached an accuracy of 0.89 and 0.90 to detect depressed and stressed users, respectively. Experimental results show that the proposed KBRS reached a rating of 94% of very satisfied users, as opposed to 69% reached by a RS without the use of neither a sentiment metric nor ontologies. Additionally, subjective test results demonstrated that the proposed solution consumes low memory, processing, and energy from current mobile electronic devices. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-10-04T15:23:58Z 2019-10-04T15:23:58Z 2019-04-01 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1109/TII.2018.2867174 Ieee Transactions On Industrial Informatics. Piscataway: Ieee-inst Electrical Electronics Engineers Inc, v. 15, n. 4, p. 2124-2135, 2019. 1551-3203 http://hdl.handle.net/11449/186268 10.1109/TII.2018.2867174 WOS:000467095500027 |
url |
http://dx.doi.org/10.1109/TII.2018.2867174 http://hdl.handle.net/11449/186268 |
identifier_str_mv |
Ieee Transactions On Industrial Informatics. Piscataway: Ieee-inst Electrical Electronics Engineers Inc, v. 15, n. 4, p. 2124-2135, 2019. 1551-3203 10.1109/TII.2018.2867174 WOS:000467095500027 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Ieee Transactions On Industrial Informatics |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
2124-2135 |
dc.publisher.none.fl_str_mv |
Ieee-inst Electrical Electronics Engineers Inc |
publisher.none.fl_str_mv |
Ieee-inst Electrical Electronics Engineers Inc |
dc.source.none.fl_str_mv |
Web of Science reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1803046624034816000 |