{"id":"https://openalex.org/W2060107295","doi":"https://doi.org/10.1145/1088622.1088625","title":"AutoFeed","display_name":"AutoFeed","publication_year":2005,"publication_date":"2005-10-02","ids":{"openalex":"https://openalex.org/W2060107295","doi":"https://doi.org/10.1145/1088622.1088625","mag":"2060107295"},"language":"en","primary_location":{"id":"doi:10.1145/1088622.1088625","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1088622.1088625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd international conference on Knowledge capture","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/A5019089688","display_name":"Bora Cenk Gazen","orcid":null},"institutions":[{"id":"https://openalex.org/I2801840469","display_name":"Torch Technologies (United States)","ror":"https://ror.org/00nrhr905","country_code":"US","type":"company","lineage":["https://openalex.org/I2801840469"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bora Gazen","raw_affiliation_strings":["Fetch Technologies, El Segundo, CA"],"affiliations":[{"raw_affiliation_string":"Fetch Technologies, El Segundo, CA","institution_ids":["https://openalex.org/I2801840469"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045363082","display_name":"Steven Minton","orcid":"https://orcid.org/0000-0001-8640-2905"},"institutions":[{"id":"https://openalex.org/I2801840469","display_name":"Torch Technologies (United States)","ror":"https://ror.org/00nrhr905","country_code":"US","type":"company","lineage":["https://openalex.org/I2801840469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Minton","raw_affiliation_strings":["Fetch Technologies, El Segundo, CA"],"affiliations":[{"raw_affiliation_string":"Fetch Technologies, El Segundo, CA","institution_ids":["https://openalex.org/I2801840469"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5019089688"],"corresponding_institution_ids":["https://openalex.org/I2801840469"],"apc_list":null,"apc_paid":null,"fwci":7.2473,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.965123,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"18","issue":null,"first_page":"3","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T13976","display_name":"Web visibility and informetrics","score":0.9848999977111816,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9757000207901001,"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":0.8360968828201294},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7495608329772949},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5819039344787598},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5587149858474731},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5321518778800964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5243273377418518},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5076214075088501},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.46947965025901794},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4667423367500305},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3391777276992798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8360968828201294},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7495608329772949},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5819039344787598},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5587149858474731},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5321518778800964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5243273377418518},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5076214075088501},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.46947965025901794},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4667423367500305},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3391777276992798},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1088622.1088625","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1088622.1088625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd international conference on Knowledge capture","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320330986","display_name":"DMTC","ror":"https://ror.org/037mj4292"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W203603362","https://openalex.org/W1487588218","https://openalex.org/W1554734378","https://openalex.org/W1577626262","https://openalex.org/W1829475407","https://openalex.org/W1921703248","https://openalex.org/W2045136577","https://openalex.org/W2093559286","https://openalex.org/W2096496923","https://openalex.org/W2104086170","https://openalex.org/W2115770258","https://openalex.org/W2119088569","https://openalex.org/W2129595335","https://openalex.org/W2135479443","https://openalex.org/W2150721933","https://openalex.org/W2160758783","https://openalex.org/W2167044614","https://openalex.org/W2799061466","https://openalex.org/W2915063781","https://openalex.org/W4230946174","https://openalex.org/W6677288352","https://openalex.org/W7014191107"],"related_works":["https://openalex.org/W3196155444","https://openalex.org/W328659180","https://openalex.org/W4321844043","https://openalex.org/W3210156800","https://openalex.org/W4390062853","https://openalex.org/W4297883248","https://openalex.org/W3209574120","https://openalex.org/W4255830763","https://openalex.org/W1583266947","https://openalex.org/W4286799911"],"abstract_inverted_index":{"Our":[0,69],"goal":[1],"is":[2,45,81],"to":[3,62],"automatically":[4],"extract":[5],"data":[6,109],"from":[7],"semi-structured":[8,108],"webn":[9],"sites.":[10],"Previously,":[11],"researchers":[12],"have":[13],"developed":[14],"two":[15],"types":[16,86],"of":[17,75,79,83,87,124,133,147],"supervised":[18],"learning":[19,61],"approaches":[20],"for":[21],"extracting":[22],"web":[23],"data:":[24],"methods":[25,33],"that":[26,34,110],"create":[27],"precise,":[28],"site-specific":[29],"extraction":[30,38],"rules":[31],"and":[32,65,106,141],"learn":[35],"less-precise":[36],"site-independent":[37],"rules.":[39],"In":[40,47],"either":[41],"case,":[42],"significant":[43],"training":[44],"required.":[46],"this":[48],"paper,":[49],"we":[50,58,119],"describe":[51],"a":[52,73,116,121,145],"third,":[53],"more":[54],"ambitious":[55],"approach,":[56,140],"where":[57],"use":[59,120],"unsupervised":[60],"analyze":[63],"sites":[64],"discover":[66],"their":[67],"structure.":[68,89],"method":[70],"relies":[71],"on":[72,98,144],"set":[74,146],"heterogeneous":[76],"\"experts\",":[77],"each":[78],"which":[80],"capable":[82],"identifying":[84],"certain":[85],"generic":[88],"Each":[90],"expert":[91],"represents":[92],"its":[93],"discoveries":[94],"as":[95],"\"hints\".":[96],"Based":[97],"these":[99],"hints,":[100],"our":[101,131,138,142],"system":[102],"clusters":[103],"the":[104,125,134],"pages":[105],"identifies":[107],"can":[111],"be":[112],"extracted.":[113],"To":[114],"identify":[115],"good":[117],"clustering,":[118],"probabilistic":[122],"model":[123],"hint-generation":[126],"process.":[127],"The":[128],"paper":[129],"describes":[130],"formulation":[132],"fully-automatic":[135],"web-extraction":[136],"problem,":[137],"clustering":[139],"results":[143],"experiments.":[148]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}