{"id":"https://openalex.org/W2605201475","doi":"https://doi.org/10.48550/arxiv.1703.07638","title":"Machine Learning Based Source Code Classification Using Syntax Oriented Features","display_name":"Machine Learning Based Source Code Classification Using Syntax Oriented Features","publication_year":2017,"publication_date":"2017-03-04","ids":{"openalex":"https://openalex.org/W2605201475","doi":"https://doi.org/10.48550/arxiv.1703.07638","mag":"2605201475"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1703.07638","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.07638","pdf_url":"https://arxiv.org/pdf/1703.07638","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1703.07638","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037318592","display_name":"Shaul Zevin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zevin, Shaul","raw_affiliation_strings":["Computer Industry"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Industry","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082094840","display_name":"Catherine Holzem","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I41156924","display_name":"Victoria University of Wellington","ror":"https://ror.org/0040r6f76","country_code":"NZ","type":"education","lineage":["https://openalex.org/I41156924"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Holzem, Catherine","raw_affiliation_strings":["Victoria University of Wellington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Victoria University of Wellington","institution_ids":["https://openalex.org/I41156924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.0,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/source-code-classification","display_name":"source code classification","score":0.9869999885559082},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"feature extraction","score":0.5659999847412109},{"id":"https://openalex.org/keywords/maximum-entropy-classifier","display_name":"maximum entropy classifier","score":0.8659999966621399},{"id":"https://openalex.org/keywords/file-extensions","display_name":"file extensions","score":0.3779999911785126},{"id":"https://openalex.org/keywords/programming-languages","display_name":"programming languages","score":0.5120000243186951}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7597721815109253},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.7145916223526001},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5672199130058289},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5516352653503418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.515963613986969},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5016939640045166},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4739760756492615},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.05780765414237976}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:1703.07638","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.07638","pdf_url":"https://arxiv.org/pdf/1703.07638","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1703.07638","doi":"https://doi.org/10.48550/arxiv.1703.07638","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1703.07638","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1703.07638","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.07638","pdf_url":"https://arxiv.org/pdf/1703.07638","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2605201475.pdf","grobid_xml":"https://content.openalex.org/works/W2605201475.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W136267437","https://openalex.org/W1550597138","https://openalex.org/W1570448133","https://openalex.org/W1859783391","https://openalex.org/W1998899601","https://openalex.org/W2237372923"],"related_works":["https://openalex.org/W7061310488","https://openalex.org/W2752033492","https://openalex.org/W2891746262","https://openalex.org/W1859783391","https://openalex.org/W7039305070","https://openalex.org/W4377427467","https://openalex.org/W4411321163","https://openalex.org/W3007026952","https://openalex.org/W4312940607","https://openalex.org/W2602842256"],"abstract_inverted_index":{"As":[0],"of":[1,6,10,104,117],"today":[2],"the":[3,7,11,23,33,51,100,118],"programming":[4,36,57,67,121],"language":[5,37,58,68],"vast":[8],"majority":[9],"published":[12],"source":[13,34],"code":[14,35],"is":[15],"manually":[16],"specified":[17],"or":[18],"programmatically":[19],"assigned":[20],"based":[21],"on":[22],"sole":[24],"file":[25],"extension.":[26],"In":[27],"this":[28],"paper":[29],"we":[30],"show":[31],"that":[32,53,86],"identification":[38,59],"task":[39],"can":[40],"be":[41],"fully":[42],"automated":[43],"using":[44],"machine":[45],"learning":[46],"techniques.":[47],"We":[48,73,107],"first":[49],"define":[50],"criteria":[52,64],"a":[54,109,124],"production-level":[55],"automatic":[56],"solution":[60],"should":[61],"meet.":[62],"Our":[63],"include":[65],"accuracy,":[66],"coverage,":[69],"extensibility":[70],"and":[71,90,102],"performance.":[72],"then":[74,91],"describe":[75],"our":[76,105],"approach:":[77],"How":[78],"training":[79,101],"files":[80],"are":[81,97],"preprocessed":[82],"for":[83,99],"extracting":[84],"features":[85],"mimic":[87],"grammar":[88,95],"productions,":[89],"how":[92],"these":[93],"extracted":[94],"productions":[96],"used":[98],"testing":[103],"classifier.":[106,127],"achieve":[108],"99":[110],"percent":[111],"accuracy":[112],"rate":[113],"while":[114],"classifying":[115],"29":[116],"most":[119],"popular":[120],"languages":[122],"with":[123],"Maximum":[125],"Entropy":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2017-04-14T00:00:00"}