{"id":"https://openalex.org/W2264942984","doi":"https://doi.org/10.1145/2824251","title":"Estimating Semantic Relatedness in Source Code","display_name":"Estimating Semantic Relatedness in Source Code","publication_year":2015,"publication_date":"2015-12-02","ids":{"openalex":"https://openalex.org/W2264942984","doi":"https://doi.org/10.1145/2824251","mag":"2264942984"},"language":"en","primary_location":{"id":"doi:10.1145/2824251","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2824251","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-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/A5037080307","display_name":"Anas Mahmoud","orcid":"https://orcid.org/0000-0001-8353-5286"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anas Mahmoud","raw_affiliation_strings":["Louisiana State University, Baton Rouge, LA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Louisiana State University, Baton Rouge, LA","institution_ids":["https://openalex.org/I121820613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112064766","display_name":"Gary Bradshaw","orcid":null},"institutions":[{"id":"https://openalex.org/I99041443","display_name":"Mississippi State University","ror":"https://ror.org/0432jq872","country_code":"US","type":"education","lineage":["https://openalex.org/I4210141039","https://openalex.org/I99041443"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gary Bradshaw","raw_affiliation_strings":["Mississippi State University, MS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mississippi State University, MS","institution_ids":["https://openalex.org/I99041443"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.4211,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.97053383,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"25","issue":"1","first_page":"1","last_page":"35"},"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/T10028","display_name":"Topic Modeling","score":0.9933000206947327,"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":0.9830999970436096,"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":0.854560136795044},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.7667237520217896},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.6084339022636414},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5998867154121399},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.542041003704071},{"id":"https://openalex.org/keywords/code-review","display_name":"Code review","score":0.5151183009147644},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49964141845703125},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.49893808364868164},{"id":"https://openalex.org/keywords/kpi-driven-code-analysis","display_name":"KPI-driven code analysis","score":0.47283560037612915},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.46913713216781616},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4336373805999756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4280220866203308},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.4182620048522949},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4070267677307129},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3529183864593506},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.335080087184906},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2754781246185303}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.854560136795044},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.7667237520217896},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.6084339022636414},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5998867154121399},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.542041003704071},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.5151183009147644},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49964141845703125},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49893808364868164},{"id":"https://openalex.org/C121957198","wikidata":"https://www.wikidata.org/wiki/Q14365593","display_name":"KPI-driven code analysis","level":5,"score":0.47283560037612915},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.46913713216781616},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4336373805999756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4280220866203308},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.4182620048522949},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4070267677307129},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3529183864593506},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.335080087184906},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2754781246185303},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2824251","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2824251","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},{"id":"pmh:oai:repository.lsu.edu:eecs_pubs-3601","is_oa":false,"landing_page_url":"https://repository.lsu.edu/eecs_pubs/2599","pdf_url":null,"source":{"id":"https://openalex.org/S4210169993","display_name":"Civil War Book Review","issn_l":"1528-6592","issn":["1528-6592"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310315936","host_organization_name":"Louisiana State University","host_organization_lineage":["https://openalex.org/P4310315936"],"host_organization_lineage_names":["Louisiana State University"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"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":112,"referenced_works":["https://openalex.org/W40976687","https://openalex.org/W55286957","https://openalex.org/W94547874","https://openalex.org/W158057341","https://openalex.org/W1490674333","https://openalex.org/W1495075807","https://openalex.org/W1500720541","https://openalex.org/W1566018662","https://openalex.org/W1567365482","https://openalex.org/W1593045043","https://openalex.org/W1593195594","https://openalex.org/W1603054740","https://openalex.org/W1647729745","https://openalex.org/W1970476061","https://openalex.org/W1971220772","https://openalex.org/W1978400666","https://openalex.org/W1979786964","https://openalex.org/W1981617416","https://openalex.org/W1983578042","https://openalex.org/W1985236007","https://openalex.org/W1988137288","https://openalex.org/W1994215021","https://openalex.org/W1995012557","https://openalex.org/W1997650168","https://openalex.org/W2004247102","https://openalex.org/W2007022086","https://openalex.org/W2012313588","https://openalex.org/W2012949377","https://openalex.org/W2014116953","https://openalex.org/W2017593508","https://openalex.org/W2019441277","https://openalex.org/W2026430933","https://openalex.org/W2026487812","https://openalex.org/W2027479172","https://openalex.org/W2038721957","https://openalex.org/W2038760838","https://openalex.org/W2040043446","https://openalex.org/W2042980227","https://openalex.org/W2045929671","https://openalex.org/W2046118959","https://openalex.org/W2060314721","https://openalex.org/W2061072593","https://openalex.org/W2061644206","https://openalex.org/W2067438047","https://openalex.org/W2074449313","https://openalex.org/W2075190746","https://openalex.org/W2077166865","https://openalex.org/W2082160726","https://openalex.org/W2085435546","https://openalex.org/W2091236368","https://openalex.org/W2096450604","https://openalex.org/W2098192829","https://openalex.org/W2099175080","https://openalex.org/W2100198805","https://openalex.org/W2100739938","https://openalex.org/W2101154344","https://openalex.org/W2103318667","https://openalex.org/W2107972503","https://openalex.org/W2109144580","https://openalex.org/W2118202700","https://openalex.org/W2120636855","https://openalex.org/W2120779048","https://openalex.org/W2121455545","https://openalex.org/W2121853854","https://openalex.org/W2121898992","https://openalex.org/W2122963002","https://openalex.org/W2123551785","https://openalex.org/W2133333349","https://openalex.org/W2134237567","https://openalex.org/W2136480620","https://openalex.org/W2136930489","https://openalex.org/W2137997906","https://openalex.org/W2138136275","https://openalex.org/W2138756793","https://openalex.org/W2141801093","https://openalex.org/W2141987989","https://openalex.org/W2142403498","https://openalex.org/W2143960295","https://openalex.org/W2144211451","https://openalex.org/W2144282912","https://openalex.org/W2145700761","https://openalex.org/W2146007434","https://openalex.org/W2147152072","https://openalex.org/W2147946282","https://openalex.org/W2149393279","https://openalex.org/W2152474046","https://openalex.org/W2153887189","https://openalex.org/W2154148563","https://openalex.org/W2163960678","https://openalex.org/W2164233915","https://openalex.org/W2165612380","https://openalex.org/W2165862892","https://openalex.org/W2165897980","https://openalex.org/W2167527590","https://openalex.org/W2167809408","https://openalex.org/W2169950128","https://openalex.org/W2170682101","https://openalex.org/W2171238733","https://openalex.org/W2261688869","https://openalex.org/W2534712034","https://openalex.org/W2536379393","https://openalex.org/W2561675875","https://openalex.org/W2594908799","https://openalex.org/W2602753196","https://openalex.org/W2756560861","https://openalex.org/W2950225692","https://openalex.org/W2953332543","https://openalex.org/W3021451495","https://openalex.org/W3216404684","https://openalex.org/W4235505822","https://openalex.org/W4285719527","https://openalex.org/W4301970156"],"related_works":["https://openalex.org/W2904997879","https://openalex.org/W1990888989","https://openalex.org/W2969257295","https://openalex.org/W20188161","https://openalex.org/W2020439121","https://openalex.org/W2909969119","https://openalex.org/W2390085541","https://openalex.org/W656101134","https://openalex.org/W4380568682","https://openalex.org/W4376482202"],"abstract_inverted_index":{"Contemporary":[0],"software":[1,152],"engineering":[2],"tools":[3,20],"exploit":[4,164],"semantic":[5,125,168,201],"relations":[6,76,130],"between":[7,131],"individual":[8],"code":[9,14,49,56,89,133,174,205,212],"terms":[10,61,68,149,213],"to":[11,34,73,87,120,160,172,236],"aid":[12],"in":[13,27,47,111,127,203],"analysis":[15],"and":[16,64,66,95,221,245],"retrieval":[17],"tasks.":[18],"Such":[19],"employ":[21],"word":[22],"similarity":[23,46,85],"methods,":[24],"often":[25,57,226],"used":[26],"natural":[28,53,83],"language":[29,84],"processing":[30],"(":[31,193],"nlp":[32],"),":[33,195],"analyze":[35],"the":[36,43,105,112,122,176,208,215,237,243,246],"textual":[37],"content":[38],"of":[39,45,107,114,167,178,211,223,234,240,249],"source":[40,48,88,132,204,229],"code.":[41,250],"However,":[42,170],"notion":[44],"is":[50,119,181],"different":[51,140],"from":[52,150],"language.":[54],"Source":[55],"includes":[58],"unnatural":[59],"domain-specific":[60],"(e.g.,":[62],"abbreviations":[63],"acronyms),":[65],"such":[67,179],"might":[69],"be":[70],"related":[71],"due":[72,171],"their":[74],"structural":[75],"rather":[77],"than":[78],"linguistic":[79],"aspects.":[80],"Therefore,":[81],"applying":[82],"methods":[86,110,141,158,162,180],"without":[90],"adjustment":[91],"can":[92],"produce":[93],"low-quality":[94],"error-prone":[96],"results.":[97],"Motivated":[98],"by":[99,206],"these":[100,186],"observations,":[101],"we":[102,188],"systematically":[103],"investigate":[104],"performance":[106,177],"several":[108],"semantic-relatedness":[109],"context":[113,224],"software.":[115],"Our":[116],"main":[117],"objective":[118],"identify":[121],"most":[123],"effective":[124],"schemes":[126],"capturing":[128],"association":[129],"terms.":[134],"To":[135,184],"provide":[136],"an":[137,196],"unbiased":[138],"comparison,":[139],"are":[142],"compared":[143],"against":[144],"human-generated":[145],"relatedness":[146,202,241],"information":[147],"using":[148],"three":[151],"systems.":[153],"Results":[154],"show":[155],"that":[156,163,199],"corpus-based":[157],"tend":[159],"outperform":[161],"external":[165],"sources":[166],"knowledge.":[169],"inherent":[173],"limitations,":[175,187],"still":[182],"suboptimal.":[183],"address":[185],"propose":[189],"Normalized":[190],"Software":[191],"Distance":[192],"nsd":[194,217],"information-theoretic":[197],"method":[198],"captures":[200],"exploiting":[207],"distributional":[209],"cues":[210],"across":[214],"system.":[216],"overcomes":[218],"data":[219],"sparsity":[220],"lack":[222],"problems":[225],"associated":[227],"with":[228],"code,":[230],"achieving":[231],"higher":[232],"levels":[233,248],"resemblance":[235],"human":[238],"perception":[239],"at":[242],"term":[244],"text":[247]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
