{"id":"https://openalex.org/W2079194772","doi":"https://doi.org/10.1145/1342211.1342234","title":"Mining business topics in source code using latent dirichlet allocation","display_name":"Mining business topics in source code using latent dirichlet allocation","publication_year":2008,"publication_date":"2008-02-19","ids":{"openalex":"https://openalex.org/W2079194772","doi":"https://doi.org/10.1145/1342211.1342234","mag":"2079194772"},"language":"en","primary_location":{"id":"doi:10.1145/1342211.1342234","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1342211.1342234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st India software engineering conference","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/A5073737610","display_name":"Girish Maskeri","orcid":null},"institutions":[{"id":"https://openalex.org/I110675161","display_name":"Infosys (India)","ror":"https://ror.org/03bs18y54","country_code":"IN","type":"company","lineage":["https://openalex.org/I110675161"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Girish Maskeri","raw_affiliation_strings":["Infosys Technologies Limited, Bangalore, India","Infosys Technologies Limited, Bangalore, India#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Infosys Technologies Limited, Bangalore, India","institution_ids":["https://openalex.org/I110675161"]},{"raw_affiliation_string":"Infosys Technologies Limited, Bangalore, India#TAB#","institution_ids":["https://openalex.org/I110675161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005045185","display_name":"Santonu Sarkar","orcid":"https://orcid.org/0000-0001-9470-7012"},"institutions":[{"id":"https://openalex.org/I110675161","display_name":"Infosys (India)","ror":"https://ror.org/03bs18y54","country_code":"IN","type":"company","lineage":["https://openalex.org/I110675161"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Santonu Sarkar","raw_affiliation_strings":["Infosys Technologies Limited, Bangalore, India","Infosys Technologies Limited, Bangalore, India#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Infosys Technologies Limited, Bangalore, India","institution_ids":["https://openalex.org/I110675161"]},{"raw_affiliation_string":"Infosys Technologies Limited, Bangalore, India#TAB#","institution_ids":["https://openalex.org/I110675161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070589644","display_name":"Kenneth Heafield","orcid":"https://orcid.org/0000-0002-6344-9927"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenneth Heafield","raw_affiliation_strings":["California Institute of Technology, CA","California Institute of Technology (CA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California Institute of Technology, CA","institution_ids":["https://openalex.org/I122411786"]},{"raw_affiliation_string":"California Institute of Technology (CA)","institution_ids":["https://openalex.org/I122411786"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":28.0225,"has_fulltext":false,"cited_by_count":171,"citation_normalized_percentile":{"value":0.99524417,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"113","last_page":"120"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9912999868392944,"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":0.9868000149726868,"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":0.9367973804473877},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.812057375907898},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.700023353099823},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.6605796217918396},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6201202869415283},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5298345685005188},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5009636878967285},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49727848172187805},{"id":"https://openalex.org/keywords/business-domain","display_name":"Business domain","score":0.49445176124572754},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.43272414803504944},{"id":"https://openalex.org/keywords/kpi-driven-code-analysis","display_name":"KPI-driven code analysis","score":0.4173544943332672},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4078899919986725},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4053117334842682},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37164002656936646},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.37027499079704285},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3552365303039551},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.31374290585517883},{"id":"https://openalex.org/keywords/static-program-analysis","display_name":"Static program analysis","score":0.2501269280910492},{"id":"https://openalex.org/keywords/business-process","display_name":"Business process","score":0.24496188759803772},{"id":"https://openalex.org/keywords/business-rule","display_name":"Business rule","score":0.20634454488754272},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20096701383590698},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.10689958930015564},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07327449321746826},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07189178466796875}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.9367973804473877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.812057375907898},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.700023353099823},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6605796217918396},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6201202869415283},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5298345685005188},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5009636878967285},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49727848172187805},{"id":"https://openalex.org/C193669473","wikidata":"https://www.wikidata.org/wiki/Q5001867","display_name":"Business domain","level":5,"score":0.49445176124572754},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.43272414803504944},{"id":"https://openalex.org/C121957198","wikidata":"https://www.wikidata.org/wiki/Q14365593","display_name":"KPI-driven code analysis","level":5,"score":0.4173544943332672},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4078899919986725},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4053117334842682},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37164002656936646},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.37027499079704285},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3552365303039551},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.31374290585517883},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.2501269280910492},{"id":"https://openalex.org/C85345410","wikidata":"https://www.wikidata.org/wiki/Q851587","display_name":"Business process","level":3,"score":0.24496188759803772},{"id":"https://openalex.org/C11066294","wikidata":"https://www.wikidata.org/wiki/Q1518244","display_name":"Business rule","level":4,"score":0.20634454488754272},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20096701383590698},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.10689958930015564},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07327449321746826},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07189178466796875},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C2778648169","wikidata":"https://www.wikidata.org/wiki/Q967768","display_name":"Compatibility (geochemistry)","level":2,"score":0.0},{"id":"https://openalex.org/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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:10.1145/1342211.1342234","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1342211.1342234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st India software engineering conference","raw_type":"proceedings-article"},{"id":"pmh:oai:authors.library.caltech.edu:72472","is_oa":false,"landing_page_url":"https://authors.library.caltech.edu/72472/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402161","display_name":"CaltechAUTHORS (California Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122411786","host_organization_name":"California Institute of Technology","host_organization_lineage":["https://openalex.org/I122411786"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Book Section"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1530498595","https://openalex.org/W1547561528","https://openalex.org/W1880262756","https://openalex.org/W1928731475","https://openalex.org/W1998899601","https://openalex.org/W2001082470","https://openalex.org/W2019912855","https://openalex.org/W2041853131","https://openalex.org/W2062947167","https://openalex.org/W2098162425","https://openalex.org/W2104924585","https://openalex.org/W2109144580","https://openalex.org/W2109154616","https://openalex.org/W2110220994","https://openalex.org/W2115941721","https://openalex.org/W2117160785","https://openalex.org/W2119109877","https://openalex.org/W2128581098","https://openalex.org/W2147152072","https://openalex.org/W2150647484","https://openalex.org/W2163960678","https://openalex.org/W2164233915","https://openalex.org/W2170798317","https://openalex.org/W2913318000","https://openalex.org/W2993781365","https://openalex.org/W4285719527","https://openalex.org/W6632663641","https://openalex.org/W6674809819"],"related_works":["https://openalex.org/W2769501189","https://openalex.org/W4315588616","https://openalex.org/W4312773271","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W3005513013","https://openalex.org/W2207653751","https://openalex.org/W2611137333","https://openalex.org/W4389543811","https://openalex.org/W4291700620"],"abstract_inverted_index":{"One":[0],"of":[1,13,45,93,121,137,150],"the":[2,11,43,46,91,138],"difficulties":[3],"in":[4,64,72,90],"maintaining":[5],"a":[6,29,52,58,100,119],"large":[7,65,95],"software":[8,96],"system":[9],"is":[10,132],"absence":[12],"documented":[14],"business":[15,74],"domain":[16,22,75,108,139],"topics":[17,23,63,76,109,140,151],"and":[18,24,98,124,141],"correlation":[19],"between":[20],"these":[21],"source":[25,78,111,123],"code.":[26,112],"Without":[27],"such":[28],"correlation,":[30],"people":[31],"without":[32],"any":[33],"prior":[34],"application":[35],"knowledge":[36],"would":[37],"find":[38],"it":[39],"hard":[40],"to":[41,134],"comprehend":[42],"functionality":[44],"system.":[47],"Latent":[48],"Dirichlet":[49],"Allocation":[50],"(LDA),":[51],"statistical":[53],"model,":[54],"has":[55,80,115],"emerged":[56],"as":[57],"popular":[59],"technique":[60],"for":[61,106,146],"discovering":[62],"text":[66],"document":[67],"corpus.":[68],"But":[69],"its":[70],"applicability":[71],"extracting":[73,107],"from":[77,110],"code":[79],"not":[81],"been":[82,116],"explored":[83],"so":[84],"far.":[85],"This":[86,113],"paper":[87],"investigates":[88],"LDA":[89,105,131],"context":[92],"comprehending":[94],"systems":[97],"proposes":[99],"human":[101],"assisted":[102],"approachbased":[103],"on":[104,118],"method":[114],"applied":[117],"number":[120],"open":[122],"proprietary":[125],"systems.":[126],"Preliminary":[127],"results":[128],"indicate":[129],"that":[130],"able":[133],"identify":[135],"some":[136],"isa":[142],"satisfactory":[143],"starting":[144],"point":[145],"further":[147],"manual":[148],"refinement":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":17},{"year":2015,"cited_by_count":17},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":18}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
