{"id":"https://openalex.org/W2132888258","doi":"https://doi.org/10.1145/1985793.1985891","title":"Experiences with text mining large collections of unstructured systems development artifacts at jpl","display_name":"Experiences with text mining large collections of unstructured systems development artifacts at jpl","publication_year":2011,"publication_date":"2011-05-21","ids":{"openalex":"https://openalex.org/W2132888258","doi":"https://doi.org/10.1145/1985793.1985891","mag":"2132888258"},"language":"en","primary_location":{"id":"doi:10.1145/1985793.1985891","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1985793.1985891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd International Conference on Software Engineering","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/A5111448882","display_name":"Dan Port","orcid":null},"institutions":[{"id":"https://openalex.org/I117965899","display_name":"University of Hawai\u02bbi at M\u0101noa","ror":"https://ror.org/01wspgy28","country_code":"US","type":"education","lineage":["https://openalex.org/I117965899"]},{"id":"https://openalex.org/I1331384533","display_name":"University of Hawaii System","ror":"https://ror.org/03tzaeb71","country_code":"US","type":"education","lineage":["https://openalex.org/I1331384533"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Port","raw_affiliation_strings":["University of Hawaii, Honolulu, HI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hawaii, Honolulu, HI, USA","institution_ids":["https://openalex.org/I117965899","https://openalex.org/I1331384533"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025137039","display_name":"Allen P. Nikora","orcid":null},"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":"Allen Nikora","raw_affiliation_strings":["California Institute of Technology, Pasadena, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California Institute of Technology, Pasadena, CA, USA","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109052234","display_name":"Jairus Hihn","orcid":null},"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":"Jairus Hihn","raw_affiliation_strings":["California Institute of Technology, Pasadena, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California Institute of Technology, Pasadena, CA, USA","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028716858","display_name":"LiGuo Huang","orcid":"https://orcid.org/0000-0001-7790-0195"},"institutions":[{"id":"https://openalex.org/I178169726","display_name":"Southern Methodist University","ror":"https://ror.org/042tdr378","country_code":"US","type":"education","lineage":["https://openalex.org/I178169726"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"LiGuo Huang","raw_affiliation_strings":["Southern Methodist University, Dallas, TX, USA","Southern Methodist University , Dallas , TX , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern Methodist University, Dallas, TX, USA","institution_ids":["https://openalex.org/I178169726"]},{"raw_affiliation_string":"Southern Methodist University , Dallas , TX , USA","institution_ids":["https://openalex.org/I178169726"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.8207,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.94206512,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"701","last_page":"710"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9955000281333923,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7108943462371826},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6405128836631775},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.6395714282989502},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6356359720230103},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5124536156654358},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4929349422454834},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3901851177215576},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.33620208501815796},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19279223680496216},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14902442693710327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7108943462371826},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6405128836631775},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.6395714282989502},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6356359720230103},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5124536156654358},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4929349422454834},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3901851177215576},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.33620208501815796},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19279223680496216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14902442693710327},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical 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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1985793.1985891","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1985793.1985891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd International Conference on Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1491587310","https://openalex.org/W1494922083","https://openalex.org/W1494946506","https://openalex.org/W1553682320","https://openalex.org/W1939280782","https://openalex.org/W1969353325","https://openalex.org/W1971656055","https://openalex.org/W1983015391","https://openalex.org/W1991650436","https://openalex.org/W2041526687","https://openalex.org/W2043811931","https://openalex.org/W2049624350","https://openalex.org/W2054520963","https://openalex.org/W2100739938","https://openalex.org/W2101080370","https://openalex.org/W2110008837","https://openalex.org/W2111093520","https://openalex.org/W2115179079","https://openalex.org/W2118202700","https://openalex.org/W2124666592","https://openalex.org/W2125598659","https://openalex.org/W2133693262","https://openalex.org/W2139379951","https://openalex.org/W2142555040","https://openalex.org/W2151747011","https://openalex.org/W2153258502","https://openalex.org/W2162493549","https://openalex.org/W2166019458","https://openalex.org/W2169451726","https://openalex.org/W2170958873","https://openalex.org/W2321048062","https://openalex.org/W2561675875","https://openalex.org/W2613863974","https://openalex.org/W4250220073","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2397288865","https://openalex.org/W2519676117","https://openalex.org/W2368524271","https://openalex.org/W2576709312","https://openalex.org/W2218202131","https://openalex.org/W2079402751","https://openalex.org/W84108837","https://openalex.org/W2392797073","https://openalex.org/W2989490741","https://openalex.org/W2023657818"],"abstract_inverted_index":{"Often":[0],"repositories":[1],"of":[2,53,74,126,133,144,155,188],"systems":[3],"engineering":[4],"artifacts":[5,165],"at":[6,77,166],"NASA's":[7],"Jet":[8],"Propulsion":[9],"Laboratory":[10],"(JPL)":[11],"are":[12],"so":[13],"large":[14,162],"and":[15,38,71,147,157,178],"poorly":[16],"structured":[17],"that":[18,81],"they":[19],"have":[20,79,102,122],"outgrown":[21],"our":[22,47,138,148],"capability":[23],"to":[24,30,45,94,137,161,169,185],"effectively":[25],"manually":[26],"process":[27,132,154],"their":[28],"contents":[29],"extract":[31],"useful":[32,83],"information.":[33],"Sophisticated":[34],"text":[35,135,159],"mining":[36,136,160],"methods":[37,56],"tools":[39],"seem":[40],"a":[41,124],"quick,":[42],"low-effort":[43],"approach":[44],"automating":[46],"limited":[48],"manual":[49],"efforts.":[50],"Our":[51],"experiences":[52],"exploring":[54],"such":[55],"mainly":[57],"in":[58,117,174,180],"three":[59],"areas":[60,187],"including":[61],"historical":[62],"risk":[63],"analysis,":[64,70],"defect":[65],"identification":[66],"based":[67],"on":[68],"requirements":[69],"over-time":[72],"analysis":[73],"system":[75,164],"anomalies":[76],"JPL,":[78],"shown":[80],"obtaining":[82],"results":[84],"requires":[85],"substantial":[86],"unanticipated":[87],"efforts":[88],"-":[89],"from":[90,111,130,152],"preprocessing":[91],"the":[92,96,131,153],"data":[93],"transforming":[95],"output":[97],"for":[98,182],"practical":[99],"applications.":[100,189],"We":[101],"not":[103],"observed":[104],"any":[105],"quick":[106],"'wins'":[107],"or":[108],"realized":[109,123],"benefit":[110,170],"short-term":[112],"effort":[113],"avoidance":[114],"through":[115],"automation":[116],"this":[118],"area.":[119],"Surprisingly":[120],"we":[121],"number":[125],"unexpected":[127],"long-term":[128],"benefits":[129,146],"applying":[134,158],"repositories.":[139],"This":[140],"paper":[141],"elaborates":[142],"some":[143],"these":[145],"important":[149],"lessons":[150],"learned":[151],"preparing":[156],"unstructured":[163],"JPL":[167],"aiming":[168],"future":[171],"TM":[172],"applications":[173],"similar":[175],"problem":[176],"domains":[177],"also":[179],"hope":[181],"being":[183],"extended":[184],"broader":[186]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}