{"id":"https://openalex.org/W2170116643","doi":"https://doi.org/10.1145/2384416.2384417","title":"Source code identifier splitting using Yahoo image and web search engine","display_name":"Source code identifier splitting using Yahoo image and web search engine","publication_year":2012,"publication_date":"2012-08-12","ids":{"openalex":"https://openalex.org/W2170116643","doi":"https://doi.org/10.1145/2384416.2384417","mag":"2170116643"},"language":"en","primary_location":{"id":"doi:10.1145/2384416.2384417","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2384416.2384417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First International Workshop on Software Mining","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/A5029699582","display_name":"Ashish Sureka","orcid":"https://orcid.org/0000-0001-6084-9661"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Ashish Sureka","raw_affiliation_strings":["Indraprastha Institute of Information Technology, Delhi (IIIT-D), New Delhi, India"],"affiliations":[{"raw_affiliation_string":"Indraprastha Institute of Information Technology, Delhi (IIIT-D), New Delhi, India","institution_ids":["https://openalex.org/I119939252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5029699582"],"corresponding_institution_ids":["https://openalex.org/I119939252"],"apc_list":null,"apc_paid":null,"fwci":0.7105,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.82572568,"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":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9991000294685364,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9991000294685364,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9948999881744385,"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":0.9911999702453613,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8037428855895996},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.759415864944458},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.602407693862915},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5395627617835999},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5317256450653076},{"id":"https://openalex.org/keywords/unique-identifier","display_name":"Unique identifier","score":0.47621282935142517},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.47158944606781006},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.46478936076164246},{"id":"https://openalex.org/keywords/semantic-search","display_name":"Semantic search","score":0.45838823914527893},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42404884099960327},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4134054481983185},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.33834928274154663},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1397170126438141},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.13052687048912048}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8037428855895996},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.759415864944458},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.602407693862915},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5395627617835999},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5317256450653076},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.47621282935142517},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.47158944606781006},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.46478936076164246},{"id":"https://openalex.org/C166423231","wikidata":"https://www.wikidata.org/wiki/Q1891170","display_name":"Semantic search","level":3,"score":0.45838823914527893},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42404884099960327},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4134054481983185},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33834928274154663},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1397170126438141},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.13052687048912048},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2384416.2384417","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2384416.2384417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First International Workshop on Software Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W53653089","https://openalex.org/W1726410169","https://openalex.org/W1972420078","https://openalex.org/W2014404979","https://openalex.org/W2022675432","https://openalex.org/W2024668171","https://openalex.org/W2099294614","https://openalex.org/W2121455545","https://openalex.org/W2128737833","https://openalex.org/W2154027310","https://openalex.org/W2155260322","https://openalex.org/W2165897980","https://openalex.org/W2171238733","https://openalex.org/W2618567416","https://openalex.org/W2914740575","https://openalex.org/W4240565647"],"related_works":["https://openalex.org/W2413568490","https://openalex.org/W1913624564","https://openalex.org/W3130054399","https://openalex.org/W4301062032","https://openalex.org/W2319837024","https://openalex.org/W2343500026","https://openalex.org/W2390627310","https://openalex.org/W2413664130","https://openalex.org/W2051731675","https://openalex.org/W2033159440"],"abstract_inverted_index":{"Source-code":[0],"or":[1,11,18,27,32,110],"program":[2],"identifiers":[3,20,58],"are":[4],"sequence":[5],"of":[6,9,56,95,100,108,137],"characters":[7],"consisting":[8],"one":[10],"more":[12],"tokens":[13],"representing":[14],"domain":[15],"concepts.":[16],"Splitting":[17],"tokenizing":[19],"that":[21,72],"does":[22],"not":[23],"contain":[24],"explicit":[25],"markers":[26],"clues":[28],"(such":[29],"as":[30,35,82,122,128],"came-casing":[31],"using":[33,59],"underscore":[34],"a":[36,40,49,96,123,135],"token":[37,102],"separator)":[38],"is":[39],"technically":[41],"challenging":[42],"problem.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47],"present":[48,69,145],"technique":[50],"for":[51],"automatic":[52],"tokenization":[53],"and":[54,63,85,91,103,117,131,144],"splitting":[55],"source-code":[57],"Yahoo":[60],"web":[61,116],"search":[62,65,111,119],"image":[64,118],"similarity":[66],"distance.":[67],"We":[68,133],"an":[70],"algorithm":[71],"decides":[73],"the":[74,89,101,115,141],"split":[75],"position":[76],"based":[77],"on":[78],"various":[79],"factors":[80],"such":[81,127],"conceptual":[83],"correlations":[84],"semantic":[86],"relatedness":[87],"between":[88],"left":[90],"right":[92],"splits":[93],"strings":[94],"given":[97],"identifier,":[98],"popularity":[99,130],"its":[104],"length.":[105],"The":[106],"number":[107],"hits":[109],"results":[112],"returned":[113],"by":[114],"engine":[120],"serves":[121],"proxy":[124],"to":[125,139],"measures":[126],"term":[129],"correlation.":[132],"perform":[134],"series":[136],"experiments":[138],"validate":[140],"proposed":[142],"approach":[143],"performance":[146],"results.":[147]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
