{"id":"https://openalex.org/W3008997415","doi":"https://doi.org/10.1109/bigdata47090.2019.9006447","title":"SoMEF: A Framework for Capturing Scientific Software Metadata from its Documentation","display_name":"SoMEF: A Framework for Capturing Scientific Software Metadata from its Documentation","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008997415","doi":"https://doi.org/10.1109/bigdata47090.2019.9006447","mag":"3008997415"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata47090.2019.9006447","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006447","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","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/A5090737533","display_name":"Allen Mao","orcid":"https://orcid.org/0000-0002-7411-7100"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Allen Mao","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033224077","display_name":"Daniel Garijo","orcid":"https://orcid.org/0000-0003-0454-7145"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Garijo","raw_affiliation_strings":["University of Southern California, Information Sciences Institute"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Information Sciences Institute","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077611411","display_name":"Shobeir Fakhraei","orcid":"https://orcid.org/0000-0001-8532-6023"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shobeir Fakhraei","raw_affiliation_strings":["University of Southern California, Information Sciences Institute"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Information Sciences Institute","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5090737533"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":1.6213,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.91751563,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3032","last_page":"3037"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.9916999936103821,"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":0.7525768280029297},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.720858633518219},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7049799561500549},{"id":"https://openalex.org/keywords/software-documentation","display_name":"Software documentation","score":0.5877635478973389},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5852643251419067},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.5223711133003235},{"id":"https://openalex.org/keywords/internal-documentation","display_name":"Internal documentation","score":0.5041295289993286},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.46374258399009705},{"id":"https://openalex.org/keywords/software-mining","display_name":"Software mining","score":0.46297189593315125},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.4545820951461792},{"id":"https://openalex.org/keywords/software-construction","display_name":"Software construction","score":0.3687071204185486},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3666362762451172},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3550233542919159},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13480934500694275}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7525768280029297},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.720858633518219},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7049799561500549},{"id":"https://openalex.org/C81587897","wikidata":"https://www.wikidata.org/wiki/Q181702","display_name":"Software documentation","level":5,"score":0.5877635478973389},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5852643251419067},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5223711133003235},{"id":"https://openalex.org/C140396857","wikidata":"https://www.wikidata.org/wiki/Q16934771","display_name":"Internal documentation","level":5,"score":0.5041295289993286},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.46374258399009705},{"id":"https://openalex.org/C103520596","wikidata":"https://www.wikidata.org/wiki/Q7554328","display_name":"Software mining","level":5,"score":0.46297189593315125},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.4545820951461792},{"id":"https://openalex.org/C186846655","wikidata":"https://www.wikidata.org/wiki/Q3398377","display_name":"Software construction","level":4,"score":0.3687071204185486},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3666362762451172},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3550233542919159},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13480934500694275}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata47090.2019.9006447","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006447","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8500000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1984922264","https://openalex.org/W2005085827","https://openalex.org/W2007959519","https://openalex.org/W2025617971","https://openalex.org/W2048315711","https://openalex.org/W2073429012","https://openalex.org/W2093647425","https://openalex.org/W2101234009","https://openalex.org/W2120755390","https://openalex.org/W2166486797","https://openalex.org/W2395669155","https://openalex.org/W3012294952","https://openalex.org/W6675354045","https://openalex.org/W6775035965"],"related_works":["https://openalex.org/W2646159910","https://openalex.org/W2602989241","https://openalex.org/W2108337646","https://openalex.org/W2404091770","https://openalex.org/W2764664989","https://openalex.org/W1489743065","https://openalex.org/W2035042871","https://openalex.org/W72470040","https://openalex.org/W2151917841","https://openalex.org/W3008997415"],"abstract_inverted_index":{"Scientific":[0],"software":[1,21,43,70,98,128,141],"has":[2],"become":[3],"a":[4,28,34,55,97,110,122,131],"key":[5],"asset":[6],"to":[7,32,45,61,80,89],"reproduce":[8],"and":[9,41,114],"understand":[10],"the":[11,64,74,90],"products":[12],"of":[13,37,68,85,96,124,139],"scientific":[14,20,69,127,140],"research":[15],"in":[16,77],"many":[17],"disciplines.":[18],"However,":[19],"is":[22],"becoming":[23],"increasingly":[24],"complex":[25],"and,":[26],"as":[27],"result,":[29],"researchers":[30],"need":[31],"spend":[33],"significant":[35],"amount":[36],"time":[38],"finding,":[39],"reading":[40],"understanding":[42],"documentation":[44],"set":[46],"it":[47],"up.":[48],"In":[49],"this":[50],"paper":[51],"we":[52],"describe":[53],"SoMEF,":[54],"Software":[56],"Metadata":[57],"Extraction":[58],"Framework":[59],"designed":[60],"help":[62],"highlighting":[63],"most":[65],"important":[66],"parts":[67,84],"documentation.":[71],"SoMEF":[72,104],"processes":[73],"README":[75,107],"files":[76],"GitHub":[78],"repositories":[79],"automatically":[81,135],"extract":[82],"which":[83],"their":[86],"text":[87],"refer":[88],"description,":[91],"installation,":[92],"invocation,":[93],"or":[94],"citation":[95],"component.":[99],"Despite":[100],"its":[101],"simple":[102],"features,":[103],"successfully":[105],"categorizes":[106],"excerpts":[108],"with":[109],"minimum":[111],"0.92":[112],"precision":[113],"0.90":[115],"ROC":[116],"AUC.":[117],"These":[118],"results,":[119],"tested":[120],"on":[121],"corpus":[123],"over":[125],"70":[126],"repositories,":[129],"are":[130],"promising":[132],"start":[133],"towards":[134],"generating":[136],"knowledge":[137],"graphs":[138],"metadata.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
