{"id":"https://openalex.org/W2798902926","doi":"https://doi.org/10.1145/3209978.3210101","title":"Parameterizing Kterm Hashing","display_name":"Parameterizing Kterm Hashing","publication_year":2018,"publication_date":"2018-06-27","ids":{"openalex":"https://openalex.org/W2798902926","doi":"https://doi.org/10.1145/3209978.3210101","mag":"2798902926"},"language":"en","primary_location":{"id":"doi:10.1145/3209978.3210101","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3209978.3210101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2208.01340","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112356189","display_name":"Dominik Wurzer","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dominik Wurzer","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069127126","display_name":"Yumeng Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yumeng Qin","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5112356189"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.1692,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58082928,"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":"945","last_page":"948"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9993000030517578,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9993000030517578,"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":0.9984999895095825,"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/T11478","display_name":"Caching and Content Delivery","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7917433977127075},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.7062416672706604},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.6959332823753357},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.5904561281204224},{"id":"https://openalex.org/keywords/novelty-detection","display_name":"Novelty detection","score":0.5570089221000671},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.49568092823028564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39782121777534485},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39748430252075195},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.3289673924446106},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3244331181049347},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2398325502872467}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7917433977127075},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7062416672706604},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.6959332823753357},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.5904561281204224},{"id":"https://openalex.org/C2778924833","wikidata":"https://www.wikidata.org/wiki/Q7064603","display_name":"Novelty detection","level":3,"score":0.5570089221000671},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.49568092823028564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39782121777534485},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39748430252075195},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.3289673924446106},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3244331181049347},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2398325502872467},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3209978.3210101","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3209978.3210101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2208.01340","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.01340","pdf_url":"https://arxiv.org/pdf/2208.01340","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2208.01340","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.01340","pdf_url":"https://arxiv.org/pdf/2208.01340","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W167016754","https://openalex.org/W841971286","https://openalex.org/W1571018273","https://openalex.org/W1594112393","https://openalex.org/W1780541288","https://openalex.org/W1860364451","https://openalex.org/W1983012012","https://openalex.org/W1996458336","https://openalex.org/W1998224037","https://openalex.org/W2006672970","https://openalex.org/W2046210419","https://openalex.org/W2048239613","https://openalex.org/W2086925418","https://openalex.org/W2087347434","https://openalex.org/W2118978333","https://openalex.org/W2123845384","https://openalex.org/W2127218421","https://openalex.org/W2135909747","https://openalex.org/W2155319834","https://openalex.org/W2250433666","https://openalex.org/W2250752175","https://openalex.org/W2462693065","https://openalex.org/W2511623037","https://openalex.org/W2930957955","https://openalex.org/W4383988640"],"related_works":["https://openalex.org/W2000601968","https://openalex.org/W2135779989","https://openalex.org/W2144265691","https://openalex.org/W2033383639","https://openalex.org/W2754607325","https://openalex.org/W3108918257","https://openalex.org/W144856782","https://openalex.org/W2080135560","https://openalex.org/W3016124764","https://openalex.org/W2147226516"],"abstract_inverted_index":{"Kterm":[0,21,48,100,114,126],"Hashing":[1,22,101,115,127],"provides":[2],"an":[3],"innovative":[4],"approach":[5],"to":[6,30,67,105],"novelty":[7,64,90],"detection":[8,36,131],"on":[9,16,43,108],"massive":[10],"data":[11,32,92],"streams.":[12,93],"Previous":[13],"research":[14],"focused":[15],"maximizing":[17],"the":[18,45,68,136],"efficiency":[19],"of":[20,47,63],"and":[23,80,122,133],"succeeded":[24],"in":[25,91,116],"scaling":[26],"First":[27,118],"Story":[28,119],"Detection":[29,120],"Twitter-size":[31],"stream":[33],"without":[34],"sacrificing":[35],"accuracy.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41,98],"focus":[42],"improving":[44],"effectiveness":[46],"Hashing.":[49],"Traditionally,":[50],"all":[51],"kterms":[52,74,106],"are":[53,75,86],"considered":[54],"as":[55],"equally":[56],"important":[57,77],"when":[58],"calculating":[59],"a":[60,117],"document's":[61],"degree":[62],"with":[65],"respect":[66],"past.":[69],"We":[70],"believe":[71],"that":[72,82,124],"certain":[73],"more":[76],"than":[78],"others":[79],"hypothesize":[81],"uniform":[83],"kterm":[84],"weights":[85,104],"sub-optimal":[87],"for":[88],"determining":[89],"To":[94],"validate":[95],"our":[96],"hypothesis,":[97],"parameterize":[99],"by":[102],"assigning":[103],"based":[107],"their":[109],"characteristics.":[110],"Our":[111],"experiments":[112],"apply":[113],"setting":[121],"reveal":[123],"parameterized":[125],"can":[128],"surpass":[129],"state-of-the-art":[130],"accuracy":[132],"significantly":[134],"outperform":[135],"uniformly":[137],"weighted":[138],"approach.":[139]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}