{"id":"https://openalex.org/W4205883273","doi":"https://doi.org/10.1109/bigdata52589.2021.9671332","title":"Machine Learning Approaches for Authorship Attribution using Source Code Stylometry","display_name":"Machine Learning Approaches for Authorship Attribution using Source Code Stylometry","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W4205883273","doi":"https://doi.org/10.1109/bigdata52589.2021.9671332"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata52589.2021.9671332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671332","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/A5010924305","display_name":"Sophia F. Frankel","orcid":null},"institutions":[{"id":"https://openalex.org/I204593131","display_name":"College of Charleston","ror":"https://ror.org/00390t168","country_code":"US","type":"education","lineage":["https://openalex.org/I204593131"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sophia F. Frankel","raw_affiliation_strings":["Department of Computer Science, College of Charleston, South Carolina, US"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of Charleston, South Carolina, US","institution_ids":["https://openalex.org/I204593131"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101771002","display_name":"Krishnendu Ghosh","orcid":"https://orcid.org/0000-0002-8471-6537"},"institutions":[{"id":"https://openalex.org/I204593131","display_name":"College of Charleston","ror":"https://ror.org/00390t168","country_code":"US","type":"education","lineage":["https://openalex.org/I204593131"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishnendu Ghosh","raw_affiliation_strings":["Department of Computer Science, College of Charleston, South Carolina, US"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of Charleston, South Carolina, US","institution_ids":["https://openalex.org/I204593131"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010924305"],"corresponding_institution_ids":["https://openalex.org/I204593131"],"apc_list":null,"apc_paid":null,"fwci":0.377,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.6114227,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3298","last_page":"3304"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9983999729156494,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9843000173568726,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10260","display_name":"Software Engineering Research","score":0.9789999723434448,"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":0.8433902859687805},{"id":"https://openalex.org/keywords/stylometry","display_name":"Stylometry","score":0.7658347487449646},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6822512745857239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6136906147003174},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5742921829223633},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5640076994895935},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5577384829521179},{"id":"https://openalex.org/keywords/authorship-attribution","display_name":"Authorship attribution","score":0.5567742586135864},{"id":"https://openalex.org/keywords/abstract-syntax-tree","display_name":"Abstract syntax tree","score":0.5530954003334045},{"id":"https://openalex.org/keywords/abstract-syntax","display_name":"Abstract syntax","score":0.5390955209732056},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.5230116248130798},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4202724099159241},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.26219913363456726}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8433902859687805},{"id":"https://openalex.org/C11192451","wikidata":"https://www.wikidata.org/wiki/Q2032038","display_name":"Stylometry","level":2,"score":0.7658347487449646},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6822512745857239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6136906147003174},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5742921829223633},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5640076994895935},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5577384829521179},{"id":"https://openalex.org/C3020202489","wikidata":"https://www.wikidata.org/wiki/Q2032038","display_name":"Authorship attribution","level":2,"score":0.5567742586135864},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.5530954003334045},{"id":"https://openalex.org/C114408938","wikidata":"https://www.wikidata.org/wiki/Q333373","display_name":"Abstract syntax","level":3,"score":0.5390955209732056},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.5230116248130798},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4202724099159241},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26219913363456726},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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:10.1109/bigdata52589.2021.9671332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671332","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1463623766","https://openalex.org/W1485912969","https://openalex.org/W1980064340","https://openalex.org/W1985086575","https://openalex.org/W2010452235","https://openalex.org/W2054126054","https://openalex.org/W2151505086","https://openalex.org/W2564822508","https://openalex.org/W2715640203","https://openalex.org/W2742956140","https://openalex.org/W2744042967","https://openalex.org/W2914961791","https://openalex.org/W2963579919","https://openalex.org/W2964150020","https://openalex.org/W2969229669","https://openalex.org/W2976414818","https://openalex.org/W3096860048","https://openalex.org/W3194447707","https://openalex.org/W4236036072","https://openalex.org/W6717158401","https://openalex.org/W6731243579"],"related_works":["https://openalex.org/W2148321854","https://openalex.org/W2342230821","https://openalex.org/W2142623242","https://openalex.org/W2352437309","https://openalex.org/W2390632043","https://openalex.org/W2588341850","https://openalex.org/W850463266","https://openalex.org/W2405053756","https://openalex.org/W4293105538","https://openalex.org/W4205883273"],"abstract_inverted_index":{"Identification":[0],"of":[1,39,56],"source":[2,20],"code":[3,21],"authorship":[4],"is":[5,16],"vital":[6],"for":[7],"attribution.":[8],"In":[9],"this":[10],"work,":[11],"a":[12],"machine":[13],"learning":[14,62],"framework":[15,24],"described":[17],"to":[18],"identify":[19],"authorship.":[22],"The":[23],"integrates":[25],"the":[26,40,44,53,57,64],"features":[27],"extracted":[28],"using":[29],"natural":[30],"language":[31],"processing":[32],"based":[33],"approaches":[34],"and":[35,60],"abstract":[36],"syntax":[37],"tree":[38],"code.":[41],"We":[42,51],"evaluate":[43],"methodology":[45],"on":[46,63],"Google":[47],"Code":[48],"Jam":[49],"dataset.":[50,65],"present":[52],"performance":[54],"measures":[55],"logistic":[58],"regression":[59],"deep":[61]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}