{"id":"https://openalex.org/W3197518744","doi":"https://doi.org/10.1007/s10664-021-10026-0","title":"Topic modeling in software engineering research","display_name":"Topic modeling in software engineering research","publication_year":2021,"publication_date":"2021-09-06","ids":{"openalex":"https://openalex.org/W3197518744","doi":"https://doi.org/10.1007/s10664-021-10026-0","mag":"3197518744"},"language":"en","primary_location":{"id":"doi:10.1007/s10664-021-10026-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-021-10026-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-021-10026-0.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10664-021-10026-0.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051431670","display_name":"Camila Costa Silva","orcid":"https://orcid.org/0000-0002-3690-1711"},"institutions":[{"id":"https://openalex.org/I185492890","display_name":"University of Canterbury","ror":"https://ror.org/03y7q9t39","country_code":"NZ","type":"education","lineage":["https://openalex.org/I185492890"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Camila Costa Silva","raw_affiliation_strings":["University of Canterbury, Christchurch, New Zealand"],"raw_orcid":"https://orcid.org/0000-0002-3690-1711","affiliations":[{"raw_affiliation_string":"University of Canterbury, Christchurch, New Zealand","institution_ids":["https://openalex.org/I185492890"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034571717","display_name":"Matthias Galster","orcid":"https://orcid.org/0000-0003-3491-1833"},"institutions":[{"id":"https://openalex.org/I185492890","display_name":"University of Canterbury","ror":"https://ror.org/03y7q9t39","country_code":"NZ","type":"education","lineage":["https://openalex.org/I185492890"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Matthias Galster","raw_affiliation_strings":["University of Canterbury, Christchurch, New Zealand"],"raw_orcid":"https://orcid.org/0000-0003-3491-1833","affiliations":[{"raw_affiliation_string":"University of Canterbury, Christchurch, New Zealand","institution_ids":["https://openalex.org/I185492890"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018823718","display_name":"Fabian Gilson","orcid":"https://orcid.org/0000-0002-1465-3315"},"institutions":[{"id":"https://openalex.org/I185492890","display_name":"University of Canterbury","ror":"https://ror.org/03y7q9t39","country_code":"NZ","type":"education","lineage":["https://openalex.org/I185492890"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Fabian Gilson","raw_affiliation_strings":["University of Canterbury, Christchurch, New Zealand"],"raw_orcid":"https://orcid.org/0000-0002-1465-3315","affiliations":[{"raw_affiliation_string":"University of Canterbury, Christchurch, New Zealand","institution_ids":["https://openalex.org/I185492890"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5018823718","https://openalex.org/A5034571717","https://openalex.org/A5051431670"],"corresponding_institution_ids":["https://openalex.org/I185492890"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":{"value":2890,"currency":"USD","value_usd":2890},"fwci":18.7819,"has_fulltext":true,"cited_by_count":90,"citation_normalized_percentile":{"value":0.9930725,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"26","issue":"6","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9991000294685364,"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":0.9991000294685364,"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.9922999739646912,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.8488719463348389},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.825839102268219},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7601156234741211},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4823321998119354},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4359695315361023},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4358827769756317},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4095330238342285},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3335392475128174},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.24918773770332336},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1004699170589447}],"concepts":[{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.8488719463348389},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.825839102268219},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7601156234741211},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4823321998119354},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4359695315361023},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4358827769756317},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4095330238342285},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3335392475128174},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.24918773770332336},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1004699170589447}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10664-021-10026-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-021-10026-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-021-10026-0.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10664-021-10026-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-021-10026-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-021-10026-0.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3197518744.pdf","grobid_xml":"https://content.openalex.org/works/W3197518744.grobid-xml"},"referenced_works_count":196,"referenced_works":["https://openalex.org/W41099606","https://openalex.org/W285841728","https://openalex.org/W1024906986","https://openalex.org/W1499516075","https://openalex.org/W1538021842","https://openalex.org/W1581639473","https://openalex.org/W1875990341","https://openalex.org/W1880262756","https://openalex.org/W1902027874","https://openalex.org/W1958077162","https://openalex.org/W1965335252","https://openalex.org/W1965484571","https://openalex.org/W1965636883","https://openalex.org/W1969486090","https://openalex.org/W1969657187","https://openalex.org/W1972978214","https://openalex.org/W1975579663","https://openalex.org/W1975790660","https://openalex.org/W1979496147","https://openalex.org/W1979991500","https://openalex.org/W1981109290","https://openalex.org/W1981629032","https://openalex.org/W1984688105","https://openalex.org/W1985266020","https://openalex.org/W1991867644","https://openalex.org/W1993344876","https://openalex.org/W1995875735","https://openalex.org/W1996901220","https://openalex.org/W1997885138","https://openalex.org/W1998130038","https://openalex.org/W1999798506","https://openalex.org/W1999910737","https://openalex.org/W2000518393","https://openalex.org/W2001082470","https://openalex.org/W2002641269","https://openalex.org/W2004192095","https://openalex.org/W2005098725","https://openalex.org/W2009977560","https://openalex.org/W2014116953","https://openalex.org/W2018663431","https://openalex.org/W2019985699","https://openalex.org/W2022371098","https://openalex.org/W2031302834","https://openalex.org/W2033771212","https://openalex.org/W2038043464","https://openalex.org/W2040411904","https://openalex.org/W2042980227","https://openalex.org/W2044429219","https://openalex.org/W2045837563","https://openalex.org/W2046799248","https://openalex.org/W2056894403","https://openalex.org/W2057587538","https://openalex.org/W2064153289","https://openalex.org/W2064772995","https://openalex.org/W2068731595","https://openalex.org/W2069131205","https://openalex.org/W2076219102","https://openalex.org/W2076264506","https://openalex.org/W2085597081","https://openalex.org/W2089468765","https://openalex.org/W2089759055","https://openalex.org/W2093400716","https://openalex.org/W2094662297","https://openalex.org/W2101819268","https://openalex.org/W2103587173","https://openalex.org/W2108545456","https://openalex.org/W2110068396","https://openalex.org/W2112143630","https://openalex.org/W2122599295","https://openalex.org/W2123549998","https://openalex.org/W2124672527","https://openalex.org/W2132827946","https://openalex.org/W2135790056","https://openalex.org/W2138824333","https://openalex.org/W2139543149","https://openalex.org/W2140264852","https://openalex.org/W2142958724","https://openalex.org/W2145382801","https://openalex.org/W2145700761","https://openalex.org/W2147152072","https://openalex.org/W2148212498","https://openalex.org/W2154071459","https://openalex.org/W2154183829","https://openalex.org/W2158266063","https://openalex.org/W2159426623","https://openalex.org/W2160528879","https://openalex.org/W2165612380","https://openalex.org/W2168332560","https://openalex.org/W2168649891","https://openalex.org/W2168894761","https://openalex.org/W2187358498","https://openalex.org/W2285477878","https://openalex.org/W2287648897","https://openalex.org/W2290968742","https://openalex.org/W2333884379","https://openalex.org/W2335783870","https://openalex.org/W2341869196","https://openalex.org/W2356036115","https://openalex.org/W2397731355","https://openalex.org/W2401967267","https://openalex.org/W2402702168","https://openalex.org/W2417608402","https://openalex.org/W2475828198","https://openalex.org/W2478191067","https://openalex.org/W2483035776","https://openalex.org/W2487391445","https://openalex.org/W2522868061","https://openalex.org/W2546780486","https://openalex.org/W2546867968","https://openalex.org/W2553051037","https://openalex.org/W2560766692","https://openalex.org/W2565718479","https://openalex.org/W2575380243","https://openalex.org/W2587676558","https://openalex.org/W2593635859","https://openalex.org/W2604738573","https://openalex.org/W2604794021","https://openalex.org/W2608489681","https://openalex.org/W2611274474","https://openalex.org/W2617730062","https://openalex.org/W2618807062","https://openalex.org/W2740330300","https://openalex.org/W2746827678","https://openalex.org/W2752012409","https://openalex.org/W2760805760","https://openalex.org/W2767795225","https://openalex.org/W2777409625","https://openalex.org/W2786424616","https://openalex.org/W2788314565","https://openalex.org/W2793175118","https://openalex.org/W2794720137","https://openalex.org/W2796115009","https://openalex.org/W2800786809","https://openalex.org/W2808975325","https://openalex.org/W2867214054","https://openalex.org/W2883213995","https://openalex.org/W2883838593","https://openalex.org/W2888241476","https://openalex.org/W2894368667","https://openalex.org/W2894963966","https://openalex.org/W2895297154","https://openalex.org/W2895555718","https://openalex.org/W2898883185","https://openalex.org/W2911293880","https://openalex.org/W2914035201","https://openalex.org/W2922093532","https://openalex.org/W2922320079","https://openalex.org/W2924175345","https://openalex.org/W2938026219","https://openalex.org/W2954300957","https://openalex.org/W2955411938","https://openalex.org/W2955797575","https://openalex.org/W2959293113","https://openalex.org/W2962771808","https://openalex.org/W2963079908","https://openalex.org/W2964244292","https://openalex.org/W2964312383","https://openalex.org/W2979307736","https://openalex.org/W2988199959","https://openalex.org/W3006284213","https://openalex.org/W3006604329","https://openalex.org/W3018447383","https://openalex.org/W3021053579","https://openalex.org/W3085238546","https://openalex.org/W3089993422","https://openalex.org/W3090050283","https://openalex.org/W3090250978","https://openalex.org/W3091658513","https://openalex.org/W3094266718","https://openalex.org/W3096162789","https://openalex.org/W3098579872","https://openalex.org/W3099845770","https://openalex.org/W3100958114","https://openalex.org/W3101548319","https://openalex.org/W3102971065","https://openalex.org/W3104077627","https://openalex.org/W3106006586","https://openalex.org/W3117242229","https://openalex.org/W3124250154","https://openalex.org/W3163411042","https://openalex.org/W4205848394","https://openalex.org/W4230995645","https://openalex.org/W4232705161","https://openalex.org/W4233135949","https://openalex.org/W4233479913","https://openalex.org/W4236122429","https://openalex.org/W4236456746","https://openalex.org/W4237247744","https://openalex.org/W4237791300","https://openalex.org/W4241580959","https://openalex.org/W4243081304","https://openalex.org/W4245826976","https://openalex.org/W4250687526","https://openalex.org/W4251166437","https://openalex.org/W4254148680","https://openalex.org/W4288079617"],"related_works":["https://openalex.org/W2610964036","https://openalex.org/W3161067528","https://openalex.org/W3079682176","https://openalex.org/W3047601251","https://openalex.org/W2947781947","https://openalex.org/W4206339242","https://openalex.org/W4292550651","https://openalex.org/W1555885145","https://openalex.org/W4313072612","https://openalex.org/W2370554703"],"abstract_inverted_index":{"Abstract":[0],"Topic":[1,71],"modeling":[2,34,72,88,97,116,161,196,212],"using":[3],"models":[4,114],"such":[5],"as":[6,162,229],"Latent":[7],"Dirichlet":[8],"Allocation":[9],"(LDA)":[10],"is":[11,239],"a":[12,25,106,155,216,237],"text":[13],"mining":[14],"technique":[15],"to":[16,38,46,56,60,66,74,152],"extract":[17],"human-readable":[18],"semantic":[19],"\u201ctopics\u201d":[20],"(i.e.,":[21,137,147],"word":[22,148],"clusters)":[23,149],"from":[24,167],"corpus":[26],"of":[27,83],"textual":[28,40,84,123,133],"documents.":[29],"In":[30],"software":[31,62,102,170],"engineering,":[32],"topic":[33,96,113,129,140,160,195,226],"has":[35,98],"been":[36,99,119,126,205],"used":[37,127],"analyze":[39],"data":[41,85,134,209],"in":[42,101,164,236],"empirical":[43],"studies":[44],"(e.g.,":[45,65,78],"find":[47],"out":[48],"what":[49],"developers":[50],"talk":[51],"about":[52],"online),":[53],"but":[54],"also":[55],"build":[57],"new":[58],"techniques":[59,117,190],"support":[61,67],"engineering":[63,103,171],"tasks":[64],"source":[68],"code":[69],"comprehension).":[70],"needs":[73],"be":[75],"applied":[76,100,163],"carefully":[77],"depending":[79],"on":[80,108,233],"the":[81,192],"type":[82],"analyzed":[86,159],"and":[87,115,142,175,181,188,201,211,218,223],"parameters).":[89],"Our":[90],"study":[91],"aims":[92],"at":[93],"describing":[94],"how":[95,132,144],"research":[104],"with":[105],"focus":[107],"four":[109],"aspects:":[110],"(1)":[111,186],"which":[112,122],"have":[118,125,204],"applied,":[120],"(2)":[121,198],"inputs":[124],"for":[128,139],"modeling,":[130,141],"(3)":[131,208],"was":[135],"\u201cprepared\u201d":[136],"pre-processed)":[138],"(4)":[143,224],"generated":[145],"topics":[146],"were":[150],"named":[151],"give":[153],"them":[154],"human-understandable":[156],"meaning.":[157],"We":[158,183],"111":[165],"papers":[166],"ten":[168],"highly-ranked":[169],"venues":[172],"(five":[173],"journals":[174],"five":[176],"conferences)":[177],"published":[178],"between":[179],"2009":[180],"2020.":[182],"found":[184],"that":[185],"LDA":[187],"LDA-based":[189],"are":[191,219],"most":[193],"frequent":[194,234],"techniques,":[197],"developer":[199],"communication":[200],"bug":[202],"reports":[203],"modelled":[206],"most,":[207],"pre-processing":[210],"parameters":[213],"vary":[214],"quite":[215],"bit":[217],"often":[220],"vaguely":[221],"reported,":[222],"manual":[225],"naming":[227],"(such":[228],"deducting":[230],"names":[231],"based":[232],"words":[235],"topic)":[238],"common.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":26},{"year":2022,"cited_by_count":12}],"updated_date":"2026-08-08T07:41:36.138363","created_date":"2025-10-10T00:00:00"}