{"id":"https://openalex.org/W4361790895","doi":"https://doi.org/10.1145/3582197.3582217","title":"Specific Search Engine Identification Model Based on Improved TF-IDF and SVM","display_name":"Specific Search Engine Identification Model Based on Improved TF-IDF and SVM","publication_year":2022,"publication_date":"2022-12-23","ids":{"openalex":"https://openalex.org/W4361790895","doi":"https://doi.org/10.1145/3582197.3582217"},"language":"en","primary_location":{"id":"doi:10.1145/3582197.3582217","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3582197.3582217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 10th International Conference on Information Technology: IoT and Smart City","raw_type":"proceedings-article"},"type":"conference-paper","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/A5058344193","display_name":"Yanting Xu","orcid":"https://orcid.org/0000-0003-3726-7502"},"institutions":[{"id":"https://openalex.org/I4210087772","display_name":"National Computer Network Emergency Response Technical Team/Coordination Center of Chinar","ror":"https://ror.org/00247dh76","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210087772"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanting Xu","raw_affiliation_strings":["Shanghai Branch of National Computer network Emergency Response technical Team/Coordination Center of China, China"],"raw_orcid":"https://orcid.org/0000-0003-3726-7502","affiliations":[{"raw_affiliation_string":"Shanghai Branch of National Computer network Emergency Response technical Team/Coordination Center of China, China","institution_ids":["https://openalex.org/I4210087772"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073780003","display_name":"Zhi Li","orcid":"https://orcid.org/0000-0003-4130-8960"},"institutions":[{"id":"https://openalex.org/I4210087772","display_name":"National Computer Network Emergency Response Technical Team/Coordination Center of Chinar","ror":"https://ror.org/00247dh76","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210087772"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Li","raw_affiliation_strings":["Shanghai Branch of National Computer network Emergency Response technical Team/Coordination Center of China, China"],"raw_orcid":"https://orcid.org/0000-0003-4130-8960","affiliations":[{"raw_affiliation_string":"Shanghai Branch of National Computer network Emergency Response technical Team/Coordination Center of China, China","institution_ids":["https://openalex.org/I4210087772"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037261269","display_name":"Xindan Wang","orcid":"https://orcid.org/0000-0002-9646-4701"},"institutions":[{"id":"https://openalex.org/I4210087772","display_name":"National Computer Network Emergency Response Technical Team/Coordination Center of Chinar","ror":"https://ror.org/00247dh76","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210087772"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xindan Wang","raw_affiliation_strings":["Shanghai Branch of National Computer network Emergency Response technical Team/Coordination Center of China, China"],"raw_orcid":"https://orcid.org/0000-0002-9646-4701","affiliations":[{"raw_affiliation_string":"Shanghai Branch of National Computer network Emergency Response technical Team/Coordination Center of China, China","institution_ids":["https://openalex.org/I4210087772"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210087772"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32241159,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"122","last_page":"126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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":0.9994999766349792,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9958000183105469,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9947999715805054,"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/search-engine","display_name":"Search engine","score":0.8543281555175781},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7342676520347595},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.7189092040061951},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.6527339816093445},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.631665050983429},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5886778831481934},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.5756248235702515},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4971487820148468},{"id":"https://openalex.org/keywords/database-search-engine","display_name":"Database search engine","score":0.49575766921043396},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48293015360832214},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4677586257457733},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4346114993095398},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35632920265197754},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3492244780063629},{"id":"https://openalex.org/keywords/metasearch-engine","display_name":"Metasearch engine","score":0.282193660736084},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.22536352276802063},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.17789453268051147}],"concepts":[{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.8543281555175781},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7342676520347595},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7189092040061951},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.6527339816093445},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.631665050983429},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5886778831481934},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.5756248235702515},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4971487820148468},{"id":"https://openalex.org/C48000682","wikidata":"https://www.wikidata.org/wiki/Q5227411","display_name":"Database search engine","level":3,"score":0.49575766921043396},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48293015360832214},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4677586257457733},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4346114993095398},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35632920265197754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3492244780063629},{"id":"https://openalex.org/C173979980","wikidata":"https://www.wikidata.org/wiki/Q114106","display_name":"Metasearch engine","level":4,"score":0.282193660736084},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.22536352276802063},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.17789453268051147},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3582197.3582217","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3582197.3582217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 10th International Conference on Information Technology: IoT and Smart City","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":2,"referenced_works":["https://openalex.org/W2612952973","https://openalex.org/W2914634430"],"related_works":["https://openalex.org/W2368945903","https://openalex.org/W2351412568","https://openalex.org/W2181560882","https://openalex.org/W2359370290","https://openalex.org/W2387073256","https://openalex.org/W4372346753","https://openalex.org/W2348885786","https://openalex.org/W2372722729","https://openalex.org/W2374021970","https://openalex.org/W4361790895"],"abstract_inverted_index":{"Search":[0],"engines":[1],"have":[2],"become":[3],"one":[4],"of":[5,23,95],"the":[6,10,21,34,44,51,76,85],"indispensable":[7],"tools":[8],"on":[9],"Internet.":[11],"A":[12],"specific":[13,93],"search":[14,24,64,78,96],"engine":[15,65],"identification":[16],"model":[17,27,86],"can":[18],"effectively":[19],"identify":[20],"types":[22,94],"engines.":[25,97],"The":[26],"constructs":[28],"website":[29,37,41,70,80],"feature":[30,46],"vectors":[31,47],"according":[32,49],"to":[33,50,57],"already":[35],"mastered":[36],"samples":[38],"and":[39],"common":[40],"samples.":[42],"And":[43],"text":[45],"calculated":[48],"improved":[52],"TF-IDF":[53],"algorithm":[54],"are":[55],"used":[56],"build":[58],"a":[59,88],"support":[60],"vector":[61],"machine":[62],"(SVM)-based":[63],"recognition":[66,90],"model.":[67],"Finally,":[68],"2,000":[69],"data":[71],"were":[72],"randomly":[73],"selected":[74],"from":[75],"300,000":[77],"engine-related":[79],"source":[81],"data.":[82],"After":[83],"verification,":[84],"has":[87],"high":[89],"rate":[91],"for":[92]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
