{"id":"https://openalex.org/W2020954030","doi":"https://doi.org/10.1109/asru.2013.6707736","title":"Automatic sentiment extraction from YouTube videos","display_name":"Automatic sentiment extraction from YouTube videos","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2020954030","doi":"https://doi.org/10.1109/asru.2013.6707736","mag":"2020954030"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2013.6707736","doi":"https://doi.org/10.1109/asru.2013.6707736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707736","pdf_url":null,"source":{"id":"https://openalex.org/S7407088663","display_name":"IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5058042844","display_name":"Lakshmish Kaushik","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lakshmish Kaushik","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), The University of Texas at Dallas (UTD), Richardson, Texas, U.S.A","Center for Robust Speech Systems (CRSS), University of Texas at Dallas (UTD), Richardson, TX, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), The University of Texas at Dallas (UTD), Richardson, Texas, U.S.A","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas (UTD), Richardson, TX, USA#TAB#","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111469714","display_name":"Abhijeet Sangwan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhijeet Sangwan","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), The University of Texas at Dallas (UTD), Richardson, Texas, U.S.A","Center for Robust Speech Systems (CRSS), University of Texas at Dallas (UTD), Richardson, TX, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), The University of Texas at Dallas (UTD), Richardson, Texas, U.S.A","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas (UTD), Richardson, TX, USA#TAB#","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), The University of Texas at Dallas (UTD), Richardson, Texas, U.S.A","Center for Robust Speech Systems (CRSS), University of Texas at Dallas (UTD), Richardson, TX, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), The University of Texas at Dallas (UTD), Richardson, Texas, U.S.A","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas (UTD), Richardson, TX, USA#TAB#","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":0.6459,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.66052395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"239","last_page":"244"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10667","display_name":"Emotion and Mood Recognition","score":0.0010000000474974513,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/sentiment-analysis","display_name":"sentiment analysis","score":0.6150000095367432},{"id":"https://openalex.org/keywords/youtube-videos","display_name":"YouTube videos","score":0.828000009059906},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.6980000138282776},{"id":"https://openalex.org/keywords/spontaneous-speech","display_name":"spontaneous speech","score":0.9350000023841858},{"id":"https://openalex.org/keywords/acoustic-modeling","display_name":"acoustic modeling","score":0.6439999938011169},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"word error rate","score":0.718999981880188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8937727808952332},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.8019367456436157},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6869417428970337},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.621185302734375},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5447460412979126},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5332823395729065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5216034650802612},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5056748390197754},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4750621020793915},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.47132256627082825},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43325096368789673},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2013.6707736","doi":"https://doi.org/10.1109/asru.2013.6707736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707736","pdf_url":null,"source":{"id":"https://openalex.org/S7407088663","display_name":"IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W104703790","https://openalex.org/W1524333225","https://openalex.org/W1590952807","https://openalex.org/W1773803948","https://openalex.org/W1988931981","https://openalex.org/W1996430422","https://openalex.org/W2036478976","https://openalex.org/W2047756776","https://openalex.org/W2085750684","https://openalex.org/W2126581182","https://openalex.org/W2160660844","https://openalex.org/W2163455955","https://openalex.org/W4205184193","https://openalex.org/W4251925141"],"related_works":["https://openalex.org/W2036478976","https://openalex.org/W2901753259","https://openalex.org/W2592109500","https://openalex.org/W4393312805","https://openalex.org/W2905894511","https://openalex.org/W4411316873","https://openalex.org/W7128219173","https://openalex.org/W4281562561","https://openalex.org/W7162459558","https://openalex.org/W4310988694"],"abstract_inverted_index":{"Extracting":[0],"speaker":[1],"sentiment":[2,59,72,89,134,153,169],"from":[3],"natural":[4],"audio":[5],"streams":[6],"such":[7],"as":[8],"YouTube":[9,61],"is":[10],"challenging.":[11],"A":[12],"number":[13],"of":[14,26,133,147,162,176],"factors":[15],"contribute":[16],"to":[17,75,87,103],"the":[18,145,159,174],"task":[19],"difficulty,":[20],"namely,":[21],"Automatic":[22],"Speech":[23],"Recognition":[24],"(ASR)":[25],"spontaneous":[27],"speech,":[28],"unknown":[29],"background":[30],"environments,":[31],"variable":[32],"source":[33],"and":[34,79,107,113,179],"channel":[35],"characteristics,":[36],"accents,":[37],"diverse":[38,81],"topics,":[39],"etc.":[40],"In":[41],"this":[42,177],"study,":[43],"we":[44,52,64,138,157],"build":[45],"upon":[46],"our":[47,120,128],"previous":[48,129],"work":[49],"[5],":[50],"where":[51],"had":[53],"proposed":[54],"a":[55,115],"system":[56,130],"for":[57,185],"detecting":[58],"in":[60,131],"videos.":[62],"Particularly,":[63],"propose":[65],"several":[66,182],"enhancements":[67,121],"including":[68],"(i)":[69],"better":[70,99],"text-based":[71],"model":[73,90],"due":[74,102],"training":[76],"on":[77,95,152],"larger":[78,116],"more":[80],"dataset,":[82],"(ii)":[83],"an":[84,123],"iterative":[85],"scheme":[86],"reduce":[88],"complexity":[91],"with":[92],"minimal":[93],"impact":[94,146],"performance":[96],"accuracy,":[97],"(iii)":[98],"speech":[100],"recognition":[101],"superior":[104],"acoustic":[105],"modeling":[106],"focused":[108],"(domain":[109],"dependent)":[110],"vocabulary/language":[111],"models,":[112],"(iv)":[114],"evaluation":[117],"dataset.":[118],"Collectively,":[119],"provide":[122],"absolute":[124],"10%":[125],"improvement":[126],"over":[127],"terms":[132],"detection":[135,154],"accuracy.":[136,155],"Additionally,":[137],"also":[139,180],"present":[140],"analysis":[141,172],"that":[142],"helps":[143],"understand":[144],"WER":[148],"(word":[149],"error":[150],"rate)":[151],"Finally,":[156],"investigate":[158],"relative":[160],"importance":[161],"different":[163],"Parts-of-Speech":[164],"(POS)":[165],"tag":[166],"features":[167],"towards":[168],"detection.":[170],"Our":[171],"reveals":[173],"practicality":[175],"technology":[178],"provides":[181],"potential":[183],"directions":[184],"future":[186],"work.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2015,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}