{"id":"https://openalex.org/W2809046027","doi":"https://doi.org/10.1145/3183440.3194997","title":"Which similarity metric to use for software documents?","display_name":"Which similarity metric to use for software documents?","publication_year":2018,"publication_date":"2018-05-27","ids":{"openalex":"https://openalex.org/W2809046027","doi":"https://doi.org/10.1145/3183440.3194997","mag":"2809046027"},"language":"en","primary_location":{"id":"doi:10.1145/3183440.3194997","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3183440.3194997","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3183440.3194997","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International Conference on Software Engineering: Companion Proceeedings","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3183440.3194997","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044363466","display_name":"Md. Masudur Rahman","orcid":"https://orcid.org/0000-0002-0931-1919"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Md Masudur Rahman","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074368173","display_name":"Saikat Chakraborty","orcid":"https://orcid.org/0000-0002-6889-7171"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saikat Chakraborty","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064541855","display_name":"Baishakhi Ray","orcid":"https://orcid.org/0000-0003-3406-5235"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baishakhi Ray","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"335","last_page":"336"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998000264167786,"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":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9976999759674072,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9945999979972839,"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":0.6830620169639587},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6547541618347168},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.613856315612793},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5137194395065308},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44421061873435974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23688653111457825},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19361087679862976},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09477075934410095}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6830620169639587},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6547541618347168},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.613856315612793},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5137194395065308},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44421061873435974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23688653111457825},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19361087679862976},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09477075934410095},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3183440.3194997","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3183440.3194997","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3183440.3194997","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International Conference on Software Engineering: Companion Proceeedings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3183440.3194997","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3183440.3194997","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3183440.3194997","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International Conference on Software Engineering: Companion Proceeedings","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6299999952316284,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G6778049706","display_name":null,"funder_award_id":"CCF-16-19123,CNS-16-18771","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2809046027.pdf","grobid_xml":"https://content.openalex.org/works/W2809046027.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W658020064","https://openalex.org/W1532325895","https://openalex.org/W1983578042","https://openalex.org/W1985947101","https://openalex.org/W2004247102","https://openalex.org/W2014415866","https://openalex.org/W2058230372","https://openalex.org/W2110220994","https://openalex.org/W2116737258","https://openalex.org/W2125980283","https://openalex.org/W2153579005","https://openalex.org/W2165612380","https://openalex.org/W2336438358","https://openalex.org/W2387719207","https://openalex.org/W2513738415","https://openalex.org/W2729710884","https://openalex.org/W2740130862","https://openalex.org/W2882319491"],"related_works":["https://openalex.org/W2384888906","https://openalex.org/W2144190808","https://openalex.org/W2376314740","https://openalex.org/W2366644548","https://openalex.org/W2357241418","https://openalex.org/W2115485936","https://openalex.org/W2119135658","https://openalex.org/W2153015554","https://openalex.org/W2103338134","https://openalex.org/W2349125667"],"abstract_inverted_index":{"Information":[0],"Retrieval":[1],"(IR)":[2],"plays":[3],"a":[4],"key":[5],"role":[6],"in":[7],"diverse":[8],"Software":[9],"Engineering":[10],"(SE)":[11],"tasks.":[12],"Similarity":[13],"metric":[14],"is":[15,55],"the":[16],"core":[17],"component":[18],"of":[19,37],"any":[20],"IR":[21],"techniques":[22],"whose":[23],"performance":[24],"differs":[25],"for":[26,64],"various":[27],"document":[28],"types.":[29],"Different":[30],"SE":[31,66],"tasks":[32],"operate":[33],"on":[34],"different":[35,65],"types":[36],"documents":[38],"like":[39],"bug":[40],"reports,":[41],"software":[42],"descriptions,":[43],"source":[44],"code,":[45],"etc.,":[46],"that":[47],"often":[48],"contain":[49],"non-standard":[50],"domain-specific":[51],"vocabulary.":[52],"Thus,":[53],"it":[54],"important":[56],"to":[57],"understand":[58],"which":[59],"similarity":[60],"metrics":[61],"are":[62],"suitable":[63],"documents.":[67]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
