Loading…

Music recommendation system based on user's sentiments extracted from social networks

In 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 posi...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on consumer electronics 2015-08, Vol.61 (3), p.359-367
Main Authors: Rosa, Renata L., Rodriguez, Demostenes Z., Bressan, Graca
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c324t-793370ef49cc2cb99f7b68ac4b3139bb2a56e7edc1773105d4ceded750ad0b7d3
cites cdi_FETCH-LOGICAL-c324t-793370ef49cc2cb99f7b68ac4b3139bb2a56e7edc1773105d4ceded750ad0b7d3
container_end_page 367
container_issue 3
container_start_page 359
container_title IEEE transactions on consumer electronics
container_volume 61
creator Rosa, Renata L.
Rodriguez, Demostenes Z.
Bressan, Graca
description In 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.
doi_str_mv 10.1109/TCE.2015.7298296
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1778014329</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>7298296</ieee_id><sourcerecordid>1778014329</sourcerecordid><originalsourceid>FETCH-LOGICAL-c324t-793370ef49cc2cb99f7b68ac4b3139bb2a56e7edc1773105d4ceded750ad0b7d3</originalsourceid><addsrcrecordid>eNpdkD1PwzAQhi0EEqWwI7FEYoAlxR9JHI-oKh9SEUs7W45zkVKSuPgcQf89rloYmKzT-7wn30PINaMzxqh6WM0XM05ZPpNclVwVJ2TC8rxMM8blKZlQqspU0EKckwvEDaUsy3k5Ieu3EVubeLCu72GoTWjdkOAOA_RJZRDqJM4jgr_DBGEIbaQCJvAdvLEhxo13fYLOtqZLBghfzn_gJTlrTIdwdXynZP20WM1f0uX78-v8cZlawbOQSiWEpNBkylpuK6UaWRWlsVklmFBVxU1egITaMikFo3mdWaihljk1Na1kLabk_rB3693nCBh036KFrjMDuBF17JXxUsFVRG__oRs3-iH-LlIxp6Us9xQ9UNY7RA-N3vq2N36nGdV7zzp61nvP-ug5Vm4OlRYA_vDf9AcChno-</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1729308789</pqid></control><display><type>article</type><title>Music recommendation system based on user's sentiments extracted from social networks</title><source>IEEE Electronic Library (IEL) Journals</source><creator>Rosa, Renata L. ; Rodriguez, Demostenes Z. ; Bressan, Graca</creator><creatorcontrib>Rosa, Renata L. ; Rodriguez, Demostenes Z. ; Bressan, Graca</creatorcontrib><description>In 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.</description><identifier>ISSN: 0098-3063</identifier><identifier>EISSN: 1558-4127</identifier><identifier>DOI: 10.1109/TCE.2015.7298296</identifier><identifier>CODEN: ITCEDA</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Data mining ; Dictionaries ; Electronics ; Energy consumption ; Measurement ; Mobile Devices ; Mood ; Music ; Recommendation System ; Recommender systems ; Sentences ; Sentiment analysis ; Social Network ; Social network services ; Social networks ; User satisfaction</subject><ispartof>IEEE transactions on consumer electronics, 2015-08, Vol.61 (3), p.359-367</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2015</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c324t-793370ef49cc2cb99f7b68ac4b3139bb2a56e7edc1773105d4ceded750ad0b7d3</citedby><cites>FETCH-LOGICAL-c324t-793370ef49cc2cb99f7b68ac4b3139bb2a56e7edc1773105d4ceded750ad0b7d3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/7298296$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,27901,27902,54771</link.rule.ids></links><search><creatorcontrib>Rosa, Renata L.</creatorcontrib><creatorcontrib>Rodriguez, Demostenes Z.</creatorcontrib><creatorcontrib>Bressan, Graca</creatorcontrib><title>Music recommendation system based on user's sentiments extracted from social networks</title><title>IEEE transactions on consumer electronics</title><addtitle>T-CE</addtitle><description>In 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.</description><subject>Data mining</subject><subject>Dictionaries</subject><subject>Electronics</subject><subject>Energy consumption</subject><subject>Measurement</subject><subject>Mobile Devices</subject><subject>Mood</subject><subject>Music</subject><subject>Recommendation System</subject><subject>Recommender systems</subject><subject>Sentences</subject><subject>Sentiment analysis</subject><subject>Social Network</subject><subject>Social network services</subject><subject>Social networks</subject><subject>User satisfaction</subject><issn>0098-3063</issn><issn>1558-4127</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2015</creationdate><recordtype>article</recordtype><recordid>eNpdkD1PwzAQhi0EEqWwI7FEYoAlxR9JHI-oKh9SEUs7W45zkVKSuPgcQf89rloYmKzT-7wn30PINaMzxqh6WM0XM05ZPpNclVwVJ2TC8rxMM8blKZlQqspU0EKckwvEDaUsy3k5Ieu3EVubeLCu72GoTWjdkOAOA_RJZRDqJM4jgr_DBGEIbaQCJvAdvLEhxo13fYLOtqZLBghfzn_gJTlrTIdwdXynZP20WM1f0uX78-v8cZlawbOQSiWEpNBkylpuK6UaWRWlsVklmFBVxU1egITaMikFo3mdWaihljk1Na1kLabk_rB3693nCBh036KFrjMDuBF17JXxUsFVRG__oRs3-iH-LlIxp6Us9xQ9UNY7RA-N3vq2N36nGdV7zzp61nvP-ug5Vm4OlRYA_vDf9AcChno-</recordid><startdate>201508</startdate><enddate>201508</enddate><creator>Rosa, Renata L.</creator><creator>Rodriguez, Demostenes Z.</creator><creator>Bressan, Graca</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope><scope>L7M</scope></search><sort><creationdate>201508</creationdate><title>Music recommendation system based on user's sentiments extracted from social networks</title><author>Rosa, Renata L. ; Rodriguez, Demostenes Z. ; Bressan, Graca</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c324t-793370ef49cc2cb99f7b68ac4b3139bb2a56e7edc1773105d4ceded750ad0b7d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2015</creationdate><topic>Data mining</topic><topic>Dictionaries</topic><topic>Electronics</topic><topic>Energy consumption</topic><topic>Measurement</topic><topic>Mobile Devices</topic><topic>Mood</topic><topic>Music</topic><topic>Recommendation System</topic><topic>Recommender systems</topic><topic>Sentences</topic><topic>Sentiment analysis</topic><topic>Social Network</topic><topic>Social network services</topic><topic>Social networks</topic><topic>User satisfaction</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Rosa, Renata L.</creatorcontrib><creatorcontrib>Rodriguez, Demostenes Z.</creatorcontrib><creatorcontrib>Bressan, Graca</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEL</collection><collection>CrossRef</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology &amp; Engineering</collection><collection>Engineering Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>IEEE transactions on consumer electronics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Rosa, Renata L.</au><au>Rodriguez, Demostenes Z.</au><au>Bressan, Graca</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Music recommendation system based on user's sentiments extracted from social networks</atitle><jtitle>IEEE transactions on consumer electronics</jtitle><stitle>T-CE</stitle><date>2015-08</date><risdate>2015</risdate><volume>61</volume><issue>3</issue><spage>359</spage><epage>367</epage><pages>359-367</pages><issn>0098-3063</issn><eissn>1558-4127</eissn><coden>ITCEDA</coden><abstract>In 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.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TCE.2015.7298296</doi><tpages>9</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0098-3063
ispartof IEEE transactions on consumer electronics, 2015-08, Vol.61 (3), p.359-367
issn 0098-3063
1558-4127
language eng
recordid cdi_proquest_miscellaneous_1778014329
source IEEE Electronic Library (IEL) Journals
subjects Data mining
Dictionaries
Electronics
Energy consumption
Measurement
Mobile Devices
Mood
Music
Recommendation System
Recommender systems
Sentences
Sentiment analysis
Social Network
Social network services
Social networks
User satisfaction
title Music recommendation system based on user's sentiments extracted from social networks
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-18T09%3A49%3A41IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Music%20recommendation%20system%20based%20on%20user's%20sentiments%20extracted%20from%20social%20networks&rft.jtitle=IEEE%20transactions%20on%20consumer%20electronics&rft.au=Rosa,%20Renata%20L.&rft.date=2015-08&rft.volume=61&rft.issue=3&rft.spage=359&rft.epage=367&rft.pages=359-367&rft.issn=0098-3063&rft.eissn=1558-4127&rft.coden=ITCEDA&rft_id=info:doi/10.1109/TCE.2015.7298296&rft_dat=%3Cproquest_cross%3E1778014329%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c324t-793370ef49cc2cb99f7b68ac4b3139bb2a56e7edc1773105d4ceded750ad0b7d3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1729308789&rft_id=info:pmid/&rft_ieee_id=7298296&rfr_iscdi=true