Please use this identifier to cite or link to this item: http://repositorio.ufla.br/jspui/handle/1/15591
Full metadata record
DC FieldValueLanguage
dc.creatorRosa, Renata Lopes-
dc.creatorRodriguez, Demostenes Zegarra-
dc.creatorBressan, Graca-
dc.date.accessioned2017-10-26T11:01:32Z-
dc.date.available2017-10-26T11:01:32Z-
dc.date.issued2015-08-
dc.identifier.citationROSA, R. L.; RODRIGUEZ, D. Z.; BRESSAN, G. Music recommendation system based on user’s sentiments extracted from social networks. IEEE Transactions on Consumer Electronics, New York, v. 61, n. 3, Aug. 2015.pt_BR
dc.identifier.urihttp://ieeexplore.ieee.org/document/7298296/pt_BR
dc.identifier.urirepositorio.ufla.br/jspui/handle/1/15591-
dc.description.abstractIn recent years, the sentiment analysis has been explored by several Internet services to recommend contents in accordance with human emotions, which are expressed through informal texts posted on social networks. However, the metrics used in the sentiment analysis only classify a sentence with positive, neutral or negative intensity, and do not detect sentiment variations in accordance with the user's profile. In this arena, this paper presents a music recommendation system based on a sentiment intensity metric, named enhanced Sentiment Metric (eSM) that is the association of a lexicon-based sentiment metric with a correction factor based on the user's profile. This correction factor is discovered by means of subjective tests, conducted in a laboratory environment. Based on the experimental results, the correction factor is formulated and used to adjust the final sentiment intensity. The users' sentiments are extracted from sentences posted on social networks and the music recommendation system is performed through a framework of low complexity for mobile devices, which suggests songs based on the current user's sentiment intensity. Also, the framework was built considering ergonomic criteria of usability. The performance of the proposed framework is evaluated with remote users using the crowdsourcing method, reaching a rating of 91% of user satisfaction, outperforming a randomly assigned song suggestion that reached 65% of user satisfaction. Furthermore, the paper presents low perceived impacts on the analysis of energy consumption, network and latency in accordance with the processing and memory perception of the recommendation system, showing advantages for the consumer electronic world.pt_BR
dc.languageen_USpt_BR
dc.publisherInstitute of Electrical and Electronics Engineerspt_BR
dc.rightsrestrictAccesspt_BR
dc.sourceIEEE Transactions on Consumer Electronicspt_BR
dc.subjectMeasurementpt_BR
dc.subjectSocial network servicespt_BR
dc.subjectSentiment analysispt_BR
dc.subjectRecommender systemspt_BR
dc.subjectDictionariespt_BR
dc.subjectDatabasespt_BR
dc.subjectMoodpt_BR
dc.titleMusic recommendation system based on user’s sentiments extracted from social networkspt_BR
dc.typeArtigopt_BR
Appears in Collections:DCC - Artigos publicados em periódicos

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.