{"id":"https://openalex.org/W2104448320","doi":"https://doi.org/10.1109/icdim.2010.5664202","title":"Topic detection in noisy data sources","display_name":"Topic detection in noisy data sources","publication_year":2010,"publication_date":"2010-07-01","ids":{"openalex":"https://openalex.org/W2104448320","doi":"https://doi.org/10.1109/icdim.2010.5664202","mag":"2104448320"},"language":"en","primary_location":{"id":"doi:10.1109/icdim.2010.5664202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2010.5664202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 Fifth International Conference on Digital Information Management (ICDIM)","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/A5024787898","display_name":"Kerstin Denecke","orcid":"https://orcid.org/0000-0001-6691-396X"},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Kerstin Denecke","raw_affiliation_strings":["L3S Research Center, Hanover, Germany","L3S Research Center, Hannover, Germany"],"affiliations":[{"raw_affiliation_string":"L3S Research Center, Hanover, Germany","institution_ids":["https://openalex.org/I4210136150"]},{"raw_affiliation_string":"L3S Research Center, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013673323","display_name":"Marko Brosowski","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marko Brosowski","raw_affiliation_strings":["L3S Research Center, Hanover, Germany","L3S Research Center, Hannover, Germany"],"affiliations":[{"raw_affiliation_string":"L3S Research Center, Hanover, Germany","institution_ids":["https://openalex.org/I4210136150"]},{"raw_affiliation_string":"L3S Research Center, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5024787898"],"corresponding_institution_ids":["https://openalex.org/I4210136150"],"apc_list":null,"apc_paid":null,"fwci":1.3531,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84838797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"50","last_page":"55"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9998999834060669,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9975000023841858,"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/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.9192878007888794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8097190856933594},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.6849151253700256},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.6497993469238281},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5556718707084656},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5054764747619629},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4856971204280853},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.47226276993751526},{"id":"https://openalex.org/keywords/hierarchical-dirichlet-process","display_name":"Hierarchical Dirichlet process","score":0.42939621210098267},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3943583369255066},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39301276206970215},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3710075616836548},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09001964330673218},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07122683525085449}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.9192878007888794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8097190856933594},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.6849151253700256},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6497993469238281},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5556718707084656},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5054764747619629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4856971204280853},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.47226276993751526},{"id":"https://openalex.org/C141318989","wikidata":"https://www.wikidata.org/wiki/Q5753066","display_name":"Hierarchical Dirichlet process","level":4,"score":0.42939621210098267},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3943583369255066},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39301276206970215},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3710075616836548},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09001964330673218},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07122683525085449},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdim.2010.5664202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2010.5664202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 Fifth International Conference on Digital Information Management (ICDIM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W72424516","https://openalex.org/W1880262756","https://openalex.org/W1907578970","https://openalex.org/W2067533161","https://openalex.org/W2068687483","https://openalex.org/W2077303393","https://openalex.org/W2113376247","https://openalex.org/W2122098402","https://openalex.org/W2129294185","https://openalex.org/W2137268161","https://openalex.org/W2138323616","https://openalex.org/W2161180563","https://openalex.org/W4231510805","https://openalex.org/W6602936745","https://openalex.org/W6639619044","https://openalex.org/W6680194728"],"related_works":["https://openalex.org/W2914864478","https://openalex.org/W2097627380","https://openalex.org/W2008338582","https://openalex.org/W4291700620","https://openalex.org/W1999586157","https://openalex.org/W22044811","https://openalex.org/W2625329765","https://openalex.org/W2255612897","https://openalex.org/W2766840109","https://openalex.org/W2955328590"],"abstract_inverted_index":{"Automatic":[0],"topic":[1,48],"detection":[2,49],"becomes":[3],"more":[4],"important":[5],"due":[6],"to":[7,17,35,44,53,68],"the":[8,15],"increase":[9],"of":[10,79,86],"information":[11],"electronically":[12],"available":[13],"and":[14,19,101],"necessity":[16],"process":[18],"filter":[20],"it.":[21],"In":[22,59],"particular,":[23],"when":[24],"language":[25],"is":[26,33,41,66],"noisy":[27,57,102],"like":[28],"in":[29,71],"weblog":[30,72],"postings,":[31],"it":[32,40],"challenging":[34],"determine":[36,69,96],"topics":[37,70,97],"correctly.":[38],"Nevertheless,":[39],"still":[42],"unclear,":[43],"what":[45],"extent":[46],"existing":[47],"algorithms":[50],"are":[51],"able":[52],"deal":[54],"with":[55],"this":[56,60,80],"material.":[58],"paper,":[61],"Latent":[62],"Dirichlet":[63],"Allocation":[64],"(LDA)":[65],"exploited":[67],"sentences.":[73,103],"We":[74],"perform":[75],"an":[76],"extensive":[77],"evaluation":[78],"algorithm":[81],"on":[82],"real":[83],"world":[84],"data":[85],"different":[87],"domains.":[88],"The":[89],"results":[90],"show":[91],"that":[92],"LDA":[93],"can":[94],"successfully":[95],"even":[98],"for":[99],"short":[100]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}