{"id":"https://openalex.org/W2165401136","doi":"https://doi.org/10.1109/msr.2009.5069496","title":"Using Latent Dirichlet Allocation for automatic categorization of software","display_name":"Using Latent Dirichlet Allocation for automatic categorization of software","publication_year":2009,"publication_date":"2009-05-01","ids":{"openalex":"https://openalex.org/W2165401136","doi":"https://doi.org/10.1109/msr.2009.5069496","mag":"2165401136"},"language":"en","primary_location":{"id":"doi:10.1109/msr.2009.5069496","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr.2009.5069496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 6th IEEE International Working Conference on Mining Software Repositories","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/A5072871314","display_name":"Kai Tian","orcid":"https://orcid.org/0009-0008-9578-8406"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Tian","raw_affiliation_strings":["Computer Science Department, The College of William and Mary, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, The College of William and Mary, VA, USA","institution_ids":["https://openalex.org/I16285277"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020432021","display_name":"Meghan Revelle","orcid":null},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meghan Revelle","raw_affiliation_strings":["Computer Science Department, The College of William and Mary, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, The College of William and Mary, VA, USA","institution_ids":["https://openalex.org/I16285277"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041262116","display_name":"Denys Poshyvanyk","orcid":"https://orcid.org/0000-0002-5626-7586"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Denys Poshyvanyk","raw_affiliation_strings":["Computer Science Department, The College of William and Mary, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, The College of William and Mary, VA, USA","institution_ids":["https://openalex.org/I16285277"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":23.293,"has_fulltext":false,"cited_by_count":176,"citation_normalized_percentile":{"value":0.99321773,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"163","last_page":"166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9930999875068665,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/computer-science","display_name":"Computer science","score":0.8213527202606201},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.7871700525283813},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7106455564498901},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.550757884979248},{"id":"https://openalex.org/keywords/perl","display_name":"Perl","score":0.5277926325798035},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5148329138755798},{"id":"https://openalex.org/keywords/software-system","display_name":"Software system","score":0.498197078704834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4889182150363922},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4650052487850189},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4307917356491089},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3624723553657532},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3531205654144287},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3358507752418518},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3322516083717346},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.2874952256679535}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8213527202606201},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.7871700525283813},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7106455564498901},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.550757884979248},{"id":"https://openalex.org/C2777002779","wikidata":"https://www.wikidata.org/wiki/Q42478","display_name":"Perl","level":2,"score":0.5277926325798035},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5148329138755798},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.498197078704834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4889182150363922},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4650052487850189},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4307917356491089},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3624723553657532},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3531205654144287},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3358507752418518},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3322516083717346},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.2874952256679535}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/msr.2009.5069496","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr.2009.5069496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 6th IEEE International Working Conference on Mining Software Repositories","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.380.5150","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.380.5150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.wm.edu/~denys/pubs/MSR2009_TianPos.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6000000238418579,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1550123627","https://openalex.org/W1880262756","https://openalex.org/W1991945471","https://openalex.org/W2004428032","https://openalex.org/W2005975241","https://openalex.org/W2036230159","https://openalex.org/W2077776641","https://openalex.org/W2079194772","https://openalex.org/W2096061896","https://openalex.org/W2109144580","https://openalex.org/W2119301379","https://openalex.org/W2126129257","https://openalex.org/W2135541598","https://openalex.org/W2147152072","https://openalex.org/W2160208252","https://openalex.org/W2173158844","https://openalex.org/W2744136779","https://openalex.org/W3143397855","https://openalex.org/W4237791300"],"related_works":["https://openalex.org/W2480056510","https://openalex.org/W2412623563","https://openalex.org/W190299232","https://openalex.org/W1521481095","https://openalex.org/W594361471","https://openalex.org/W2604964690","https://openalex.org/W2417897055","https://openalex.org/W2613359208","https://openalex.org/W2291334382","https://openalex.org/W1484205720"],"abstract_inverted_index":{"In":[0,51,93],"this":[1],"paper,":[2],"we":[3,47,97],"propose":[4],"a":[5,163],"technique":[6],"called":[7],"LACT":[8,17,55,79,99,121,146],"for":[9,63,126],"automatically":[10,81],"categorizing":[11],"software":[12,66,102,131],"systems":[13,67,103,132],"in":[14,69,105],"open-source":[15],"repositories.":[16],"is":[18,29,162],"based":[19,154],"on":[20,155],"latent":[21],"Dirichlet":[22],"Allocation,":[23],"an":[24,44,59],"information":[25],"retrieval":[26],"method":[27],"which":[28,161],"used":[30,124],"to":[31,91,100,168],"index":[32],"and":[33,86,115,171],"analyze":[34],"source":[35],"code":[36],"documents":[37],"as":[38,110,166],"mixtures":[39],"of":[40,130,134],"probabilistic":[41],"topics.":[42],"For":[43],"initial":[45],"evaluation,":[46],"performed":[48],"two":[49],"studies.":[50],"the":[52,94,127,135],"first":[53],"study,":[54,96],"was":[56],"compared":[57,167],"against":[58],"existing":[60,172],"tool,":[61],"MUDABlue,":[62],"classifying":[64],"41":[65],"written":[68,104],"C":[70],"into":[71],"problem":[72],"domain":[73],"categories.":[74],"The":[75,117],"results":[76,89,118],"indicate":[77,119,144],"that":[78,120,145,152],"can":[80,122,147],"produce":[82],"meaningful":[83],"category":[84],"names":[85],"yield":[87],"classification":[88],"comparable":[90],"MUDABlue.":[92],"second":[95],"applied":[98],"43":[101],"different":[106],"programming":[107,137,159],"languages":[108],"such":[109],"C/C++,":[111],"Java,":[112],"C#,":[113],"PHP,":[114],"Perl.":[116],"be":[123],"effectively":[125],"automatic":[128],"categorization":[129,170],"regardless":[133],"underlying":[136],"language":[138],"or":[139,158],"paradigm.":[140],"Moreover,":[141],"both":[142],"studies":[143],"identify":[148],"several":[149],"new":[150],"categories":[151],"are":[153],"libraries,":[156],"architectures,":[157],"languages,":[160],"promising":[164],"improvement":[165],"manual":[169],"techniques.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":16},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":14}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}