{"id":"https://openalex.org/W2018582844","doi":"https://doi.org/10.1145/2597073.2597088","title":"Improving the accuracy of duplicate bug report detection using textual similarity measures","display_name":"Improving the accuracy of duplicate bug report detection using textual similarity measures","publication_year":2014,"publication_date":"2014-05-20","ids":{"openalex":"https://openalex.org/W2018582844","doi":"https://doi.org/10.1145/2597073.2597088","mag":"2018582844"},"language":"en","primary_location":{"id":"doi:10.1145/2597073.2597088","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2597073.2597088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Working Conference on Mining Software Repositories","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/A5056799505","display_name":"Alina Lazar","orcid":"https://orcid.org/0000-0002-2096-1541"},"institutions":[{"id":"https://openalex.org/I161203489","display_name":"Youngstown State University","ror":"https://ror.org/038zf2n28","country_code":"US","type":"education","lineage":["https://openalex.org/I161203489"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alina Lazar","raw_affiliation_strings":["Youngstown State University, USA","Youngstown State University , USA"],"affiliations":[{"raw_affiliation_string":"Youngstown State University, USA","institution_ids":["https://openalex.org/I161203489"]},{"raw_affiliation_string":"Youngstown State University , USA","institution_ids":["https://openalex.org/I161203489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110118783","display_name":"Sarah Ritchey","orcid":null},"institutions":[{"id":"https://openalex.org/I161203489","display_name":"Youngstown State University","ror":"https://ror.org/038zf2n28","country_code":"US","type":"education","lineage":["https://openalex.org/I161203489"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarah Ritchey","raw_affiliation_strings":["Youngstown State University, USA","Youngstown State University , USA"],"affiliations":[{"raw_affiliation_string":"Youngstown State University, USA","institution_ids":["https://openalex.org/I161203489"]},{"raw_affiliation_string":"Youngstown State University , USA","institution_ids":["https://openalex.org/I161203489"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045476556","display_name":"Bonita Sharif","orcid":"https://orcid.org/0000-0002-5178-7160"},"institutions":[{"id":"https://openalex.org/I161203489","display_name":"Youngstown State University","ror":"https://ror.org/038zf2n28","country_code":"US","type":"education","lineage":["https://openalex.org/I161203489"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bonita Sharif","raw_affiliation_strings":["Youngstown State University, USA","Youngstown State University , USA"],"affiliations":[{"raw_affiliation_string":"Youngstown State University, USA","institution_ids":["https://openalex.org/I161203489"]},{"raw_affiliation_string":"Youngstown State University , USA","institution_ids":["https://openalex.org/I161203489"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056799505"],"corresponding_institution_ids":["https://openalex.org/I161203489"],"apc_list":null,"apc_paid":null,"fwci":14.9891,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":{"value":0.98668926,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"308","last_page":"311"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9793999791145325,"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/T10028","display_name":"Topic Modeling","score":0.9745000004768372,"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/computer-science","display_name":"Computer science","score":0.7804805040359497},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7406030893325806},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5634199380874634},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5525653958320618},{"id":"https://openalex.org/keywords/eclipse","display_name":"Eclipse","score":0.5452393293380737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48853787779808044},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4790005385875702},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45882463455200195},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.44897571206092834},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4137857258319855},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.24085670709609985},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.12463876605033875},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.0816546082496643}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7804805040359497},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7406030893325806},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5634199380874634},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5525653958320618},{"id":"https://openalex.org/C2778505590","wikidata":"https://www.wikidata.org/wiki/Q141022","display_name":"Eclipse","level":2,"score":0.5452393293380737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48853787779808044},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4790005385875702},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45882463455200195},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.44897571206092834},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4137857258319855},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.24085670709609985},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.12463876605033875},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0816546082496643},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2597073.2597088","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2597073.2597088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Working Conference on Mining Software Repositories","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1942015218","https://openalex.org/W1999910737","https://openalex.org/W2125587588","https://openalex.org/W2130146200","https://openalex.org/W2133108681","https://openalex.org/W2139270835","https://openalex.org/W2153635508","https://openalex.org/W2165022036","https://openalex.org/W2167630669","https://openalex.org/W2997591727"],"related_works":["https://openalex.org/W137217271","https://openalex.org/W91167106","https://openalex.org/W4250943967","https://openalex.org/W4299375876","https://openalex.org/W1492637474","https://openalex.org/W2952911668","https://openalex.org/W1809480526","https://openalex.org/W1977280627","https://openalex.org/W4232878093","https://openalex.org/W2328392046"],"abstract_inverted_index":{"The":[0],"paper":[1],"describes":[2],"an":[3],"improved":[4,61],"method":[5,84],"for":[6],"automatic":[7],"duplicate":[8],"bug":[9],"report":[10],"detection":[11],"based":[12],"on":[13,45],"new":[14,25],"textual":[15,26],"similarity":[16,32],"features":[17],"and":[18,53,74],"binary":[19,37],"classification.":[20],"Using":[21],"a":[22],"set":[23],"of":[24,59,81],"features,":[27],"inspired":[28],"from":[29],"recent":[30],"text":[31],"research,":[33],"we":[34],"train":[35],"several":[36],"classification":[38],"models.":[39],"A":[40,63],"case":[41],"study":[42],"was":[43],"conducted":[44],"three":[46,95],"open":[47],"source":[48],"systems:":[49],"Eclipse,":[50],"Open":[51],"Office,":[52],"Mozilla":[54],"to":[55,93],"determine":[56],"the":[57,60,79,82],"effectiveness":[58],"method.":[62],"comparison":[64],"is":[65,85],"also":[66],"made":[67],"with":[68,91],"current":[69],"state-of-the-art":[70],"approaches":[71],"highlighting":[72],"similarities":[73],"differences.":[75],"Results":[76],"indicate":[77],"that":[78],"accuracy":[80],"proposed":[83],"better":[86],"than":[87],"previously":[88],"reported":[89],"research":[90],"respect":[92],"all":[94],"systems.":[96]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}