{"id":"https://openalex.org/W2810765652","doi":null,"title":"Mining Programming Language Vocabularies from Source Code.","display_name":"Mining Programming Language Vocabularies from Source Code.","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2810765652","mag":"2810765652"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.222.8438","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.222.8438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ppig.org/papers/21st-delorey.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5039789727","display_name":"Daniel P. Delorey","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel P. Delorey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075040423","display_name":"Charles D. Knutson","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Charles D. Knutson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Mark Davies","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Davies","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5272,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.77003309,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"12","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":0.9994999766349792,"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":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":9.999999747378752e-05,"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.0,"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/source-code-mining","display_name":"source code mining","score":0.7689999938011169},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"corpus linguistics","score":0.8420000076293945},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.5379999876022339},{"id":"https://openalex.org/keywords/program-comprehension","display_name":"program comprehension","score":0.6150000095367432},{"id":"https://openalex.org/keywords/source-code-repositories","display_name":"software repositories","score":0.4819999933242798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6784889698028564},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6101717352867126},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5379719138145447},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.46996399760246277},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.464357852935791},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34133654832839966},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2035984992980957}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.222.8438","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.222.8438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ppig.org/papers/21st-delorey.pdf","raw_type":"text"},{"id":"mag:2810765652","doi":null,"is_oa":false,"landing_page_url":"http://ppig.org/library/paper/mining-programming-language-vocabularies-source-code","pdf_url":null,"source":{"id":"https://openalex.org/S4306522928","display_name":"PPIG","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"PPIG","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W84249500","https://openalex.org/W566799317","https://openalex.org/W1244965290","https://openalex.org/W1568450719","https://openalex.org/W1967461618","https://openalex.org/W1969020117","https://openalex.org/W2023403404","https://openalex.org/W2045922551","https://openalex.org/W2074350771","https://openalex.org/W2084056172","https://openalex.org/W2096636321","https://openalex.org/W2102619495","https://openalex.org/W2104630935","https://openalex.org/W2158324307","https://openalex.org/W2159651246","https://openalex.org/W2163724607","https://openalex.org/W2784484269","https://openalex.org/W2958814800","https://openalex.org/W2983995785"],"related_works":["https://openalex.org/W4308643003","https://openalex.org/W3128329727","https://openalex.org/W7140795324","https://openalex.org/W7100594240","https://openalex.org/W3005064642","https://openalex.org/W2807585453","https://openalex.org/W7101147178","https://openalex.org/W2096657610","https://openalex.org/W3111699480","https://openalex.org/W7120400283"],"abstract_inverted_index":{"Abstract.":[0],"We":[1,124],"can":[2,154],"learn":[3],"much":[4],"from":[5,31],"the":[6,10,28,32,38,56,60,71,91,95,101,107,129,136,159,171,184,202,222],"artifacts":[7],"produced":[8],"as":[9],"by-products":[11],"of":[12,27,34,65,73,94,138,145,212,221],"software":[13,18],"development":[14],"and":[15,196,206],"stored":[16],"in":[17,100,120,135],"repositories.":[19],"Of":[20],"all":[21],"such":[22],"potential":[23],"data":[24,44,193,198],"sources,":[25],"one":[26],"most":[29,61],"important":[30],"perspective":[33],"program":[35,53],"comprehension":[36],"is":[37,59,104,163],"source":[39,57,81,150],"code":[40,58,151],"itself.":[41],"While":[42],"other":[43],"sources":[45],"give":[46],"insight":[47],"into":[48,158],"what":[49,66],"developers":[50],"intend":[51],"a":[52,79,117,121,143,197],"to":[54,77,115,142,178],"do,":[55],"accurate":[62],"human-accessible":[63],"description":[64],"it":[67],"will":[68],"do.":[69],"However,":[70],"ability":[72],"an":[74,209,213],"individual":[75],"developer":[76],"comprehend":[78],"particular":[80],"file":[82],"depends":[83],"directly":[84],"on":[85,218],"his":[86],"or":[87],"her":[88],"familiarity":[89],"with":[90],"specific":[92],"features":[93],"programming":[96,146,164,179,189,204],"language":[97,140,147,180],"being":[98],"used":[99,131],"file.":[102],"This":[103],"not":[105],"unlike":[106],"difficulties":[108],"second-language":[109],"learners":[110],"may":[111],"encounter":[112],"when":[113],"attempting":[114],"read":[116],"text":[118],"written":[119],"new":[122,156],"language.":[123,165],"propose":[125],"that":[126,162],"by":[127,132,181],"applying":[128,174],"techniques":[130],"corpus":[133,144,175,216],"linguists":[134],"study":[137],"natural":[139],"texts":[141,148],"(i.e.,":[149],"repositories),":[152],"we":[153,169],"gain":[155],"insights":[157],"communication":[160],"medium":[161],"In":[166],"this":[167],"paper":[168],"lay":[170],"foundation":[172],"for":[173,188,201],"linguistic":[176,215],"methods":[177],"1)":[182],"defining":[183],"term":[185],"\u201cword":[186],"\u201d":[187],"language,":[190,205],"2)":[191],"developing":[192],"collection":[194],"tools":[195],"storage":[199],"schema":[200],"Java":[203,223],"3)":[207],"presenting":[208],"initial":[210],"analysis":[211],"example":[214],"based":[217],"version":[219],"1.5":[220],"Developers":[224],"Kit.":[225],"1":[226]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1}],"updated_date":"2026-09-29T14:09:16.559479","created_date":"2018-07-10T00:00:00"}
