{"id":"https://openalex.org/W2147658782","doi":"https://doi.org/10.1145/2517288.2517293","title":"Contextual rule-based feature engineering for author-paper identification","display_name":"Contextual rule-based feature engineering for author-paper identification","publication_year":2013,"publication_date":"2013-08-11","ids":{"openalex":"https://openalex.org/W2147658782","doi":"https://doi.org/10.1145/2517288.2517293","mag":"2147658782"},"language":"en","primary_location":{"id":"doi:10.1145/2517288.2517293","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2517288.2517293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 KDD Cup 2013 Workshop","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/A5053654789","display_name":"Erheng Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Erheng Zhong","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103228158","display_name":"Lianghao Li","orcid":"https://orcid.org/0000-0002-7819-7910"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lianghao Li","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100742122","display_name":"Naiyan Wang","orcid":"https://orcid.org/0000-0002-0526-3331"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Naiyan Wang","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012486709","display_name":"Ben Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ben Tan","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103141925","display_name":"Yin Zhu","orcid":"https://orcid.org/0000-0001-7861-4203"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yin Zhu","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021558189","display_name":"Lili Zhao","orcid":"https://orcid.org/0000-0002-5182-7230"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lili Zhao","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100636286","display_name":"Qiang Yang","orcid":"https://orcid.org/0000-0001-5059-8360"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qiang Yang","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong and Huawei Noah's Ark Lab, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong and Huawei Noah's Ark Lab, Hong Kong","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.24395604,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9975000023841858,"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/T10028","display_name":"Topic Modeling","score":0.9965999722480774,"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":0.8341453075408936},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.7080724239349365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6899124979972839},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6757115125656128},{"id":"https://openalex.org/keywords/divide-and-conquer-algorithms","display_name":"Divide and conquer algorithms","score":0.5294862389564514},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5112636089324951},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.49298569560050964},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46069571375846863},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.44146937131881714},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41365504264831543},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3715342581272125},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.19777262210845947}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8341453075408936},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.7080724239349365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6899124979972839},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6757115125656128},{"id":"https://openalex.org/C71559656","wikidata":"https://www.wikidata.org/wiki/Q671298","display_name":"Divide and conquer algorithms","level":2,"score":0.5294862389564514},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5112636089324951},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.49298569560050964},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46069571375846863},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.44146937131881714},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41365504264831543},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3715342581272125},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.19777262210845947},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2517288.2517293","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2517288.2517293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 KDD Cup 2013 Workshop","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-61132","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-61132","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.400.739","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.400.739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.kdd.org/kddcup2013/sites/default/files/papers/track1place6.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W75690293","https://openalex.org/W1485815177","https://openalex.org/W1973435495","https://openalex.org/W1975258157","https://openalex.org/W2008183828","https://openalex.org/W2037417802","https://openalex.org/W2070493638","https://openalex.org/W2115584760","https://openalex.org/W2116690618","https://openalex.org/W2135223301","https://openalex.org/W2145893390","https://openalex.org/W2149427297","https://openalex.org/W2168278308","https://openalex.org/W2407494849","https://openalex.org/W2884475480","https://openalex.org/W6659889469","https://openalex.org/W6677385034","https://openalex.org/W6747597888"],"related_works":["https://openalex.org/W2352794675","https://openalex.org/W1539994214","https://openalex.org/W2051228988","https://openalex.org/W4247094814","https://openalex.org/W108531593","https://openalex.org/W2111712077","https://openalex.org/W8810113","https://openalex.org/W2158636562","https://openalex.org/W2162911572","https://openalex.org/W2019464130"],"abstract_inverted_index":{"We":[0,19,59],"present":[1],"the":[2,11,22,34,74,83,125,136,142],"ideas":[3],"and":[4,29,105],"methodologies":[5],"that":[6,73,98],"we":[7,71,90,115],"used":[8],"to":[9,32,45,78,119],"address":[10],"KDD":[12],"Cup":[13],"2013":[14],"challenge":[15],"on":[16,56,102],"author-paper":[17],"identification.":[18],"firstly":[20],"formulate":[21,91],"problem":[23],"as":[24,64,94,133,135],"a":[25,37,52,95],"personalized":[26],"ranking":[27],"task":[28,35],"then":[30],"propose":[31],"solve":[33],"through":[36],"supervised":[38],"learning":[39,108],"framework.":[40],"The":[41],"key":[42],"point":[43],"is":[44,82],"eliminate":[46],"those":[47],"incorrectly":[48],"assigned":[49],"papers":[50],"of":[51],"given":[53],"author":[54],"based":[55,101,130],"existing":[57],"records.":[58],"choose":[60],"Gradient":[61],"Boosted":[62],"Tree":[63],"our":[65,69,80],"main":[66],"classifier.":[67],"Through":[68],"exploration":[70],"conclude":[72],"most":[75],"critical":[76],"factor":[77],"achieve":[79],"results":[81,127],"effective":[84],"feature":[85],"engineering.":[86],"In":[87],"this":[88,92],"paper,":[89],"process":[93],"unified":[96],"framework":[97],"constructs":[99],"features":[100],"contextual":[103],"information":[104],"combines":[106],"machine":[107],"techniques":[109,139],"with":[110],"human":[111],"intelligence.":[112],"Besides":[113],"this,":[114],"suggest":[116],"several":[117],"strategies":[118],"parse":[120],"authors'":[121],"names,":[122],"which":[123],"improve":[124],"prediction":[126,143],"significantly.":[128],"Divide-conquer":[129],"model":[131,137],"building":[132],"well":[134],"averaging":[138],"also":[140],"benefit":[141],"precision.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
