{"id":"https://openalex.org/W2012665501","doi":"https://doi.org/10.1145/1816123.1816146","title":"Improving mood classification in music digital libraries by combining lyrics and audio","display_name":"Improving mood classification in music digital libraries by combining lyrics and audio","publication_year":2010,"publication_date":"2010-06-21","ids":{"openalex":"https://openalex.org/W2012665501","doi":"https://doi.org/10.1145/1816123.1816146","mag":"2012665501"},"language":"en","primary_location":{"id":"doi:10.1145/1816123.1816146","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1816123.1816146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th annual joint conference on Digital libraries","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052775912","display_name":"Xiao Hu","orcid":"https://orcid.org/0000-0003-3994-0385"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiao Hu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA","University of Illinois at Urbana-Champaign, Champaign, IL, USA;"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA;","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016957740","display_name":"J. Stephen Downie","orcid":"https://orcid.org/0000-0001-9784-5090"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Stephen Downie","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA","University of Illinois at Urbana-Champaign, Champaign, IL, USA;"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA;","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5052775912"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":7.44,"has_fulltext":false,"cited_by_count":113,"citation_normalized_percentile":{"value":0.97783564,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"159","last_page":"168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.9730997085571289},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7077075839042664},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.7018930912017822},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6472113728523254},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.6313266754150391},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5929481387138367},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5121035575866699},{"id":"https://openalex.org/keywords/mood","display_name":"Mood","score":0.45275944471359253},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41435885429382324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3910609185695648},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3397016227245331},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3337404727935791},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.22539561986923218},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1610758900642395},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.12857940793037415},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.12168022990226746},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08978945016860962},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.08760148286819458},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.07374894618988037}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.9730997085571289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7077075839042664},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.7018930912017822},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6472113728523254},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.6313266754150391},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5929481387138367},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5121035575866699},{"id":"https://openalex.org/C2780733359","wikidata":"https://www.wikidata.org/wiki/Q331769","display_name":"Mood","level":2,"score":0.45275944471359253},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41435885429382324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3910609185695648},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3397016227245331},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3337404727935791},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.22539561986923218},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1610758900642395},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.12857940793037415},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.12168022990226746},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08978945016860962},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.08760148286819458},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.07374894618988037},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1816123.1816146","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1816123.1816146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th annual joint conference on Digital libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:hub.hku.hk:10722/180711","is_oa":false,"landing_page_url":"http://hdl.handle.net/10722/180711","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference_Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8600000143051147}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306146","display_name":"Andrew W. Mellon Foundation","ror":"https://ror.org/04jsh2530"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W80497942","https://openalex.org/W113940810","https://openalex.org/W168039245","https://openalex.org/W168588848","https://openalex.org/W179394430","https://openalex.org/W184851609","https://openalex.org/W769016527","https://openalex.org/W1522051624","https://openalex.org/W1524281572","https://openalex.org/W1566337733","https://openalex.org/W1595803501","https://openalex.org/W1601807985","https://openalex.org/W1948749636","https://openalex.org/W2001014535","https://openalex.org/W2014470830","https://openalex.org/W2014507236","https://openalex.org/W2031253971","https://openalex.org/W2038721957","https://openalex.org/W2075718943","https://openalex.org/W2082291422","https://openalex.org/W2088353053","https://openalex.org/W2089159047","https://openalex.org/W2097726431","https://openalex.org/W2104190448","https://openalex.org/W2144707026","https://openalex.org/W2148600927","https://openalex.org/W2149628368","https://openalex.org/W2153635508","https://openalex.org/W2157236054","https://openalex.org/W2165766797","https://openalex.org/W2318570689","https://openalex.org/W2404480901","https://openalex.org/W4205184193","https://openalex.org/W4255115313","https://openalex.org/W4285719527","https://openalex.org/W6622442462","https://openalex.org/W7056632056"],"related_works":["https://openalex.org/W2994064478","https://openalex.org/W2144707026","https://openalex.org/W112239495","https://openalex.org/W2542820473","https://openalex.org/W2515398186","https://openalex.org/W2130068930","https://openalex.org/W3081404490","https://openalex.org/W2012665501","https://openalex.org/W4212956476","https://openalex.org/W1833351015"],"abstract_inverted_index":{"Mood":[0],"is":[1],"an":[2],"emerging":[3],"metadata":[4],"type":[5],"and":[6,14,37,48,75,132,154,159],"access":[7,166],"point":[8,167],"in":[9,31,168],"music":[10,16,32,63,156,169],"digital":[11,170],"libraries":[12],"(MDL)":[13],"online":[15],"repositories.":[17],"In":[18,83],"this":[19],"study,":[20],"we":[21],"present":[22],"a":[23,39,122,164],"comprehensive":[24],"investigation":[25],"of":[26,29,42,87,126],"the":[27,55,85,92,104,148],"usefulness":[28],"lyrics":[30,74,113,133],"mood":[33,138,157,163],"classification":[34,108,158],"by":[35],"evaluating":[36],"comparing":[38],"wide":[40],"range":[41],"lyric":[43,57,94,151],"text":[44,49],"features":[45,58,60],"including":[46],"linguistic":[47],"stylistic":[50],"features.":[51,82],"We":[52],"then":[53],"combine":[54],"best":[56],"with":[59],"extracted":[61],"from":[62,141],"audio":[64,76,96,115,131],"using":[65,80,112],"two":[66],"fusion":[67],"methods.":[68],"The":[69,144],"results":[70],"show":[71],"that":[72,91],"combining":[73],"significantly":[77],"outperformed":[78],"systems":[79,111],"audio-only":[81],"addition,":[84],"examination":[86],"learning":[88],"curves":[89],"shows":[90],"hybrid":[93],"+":[95],"system":[97],"needed":[98],"fewer":[99],"training":[100],"samples":[101],"to":[102],"achieve":[103],"same":[105],"or":[106,114],"better":[107],"accuracies":[109],"than":[110],"singularly.":[116],"These":[117],"experiments":[118],"were":[119],"conducted":[120],"on":[121,150],"unique":[123],"large-scale":[124],"dataset":[125],"5,296":[127],"songs":[128],"(with":[129],"both":[130],"for":[134],"each)":[135],"representing":[136],"18":[137],"categories":[139],"derived":[140],"social":[142],"tags.":[143],"findings":[145],"push":[146],"forward":[147],"state-of-the-art":[149],"sentiment":[152],"analysis":[153],"automatic":[155],"will":[160],"help":[161],"make":[162],"practical":[165],"libraries.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}