{"id":"https://openalex.org/W2138405339","doi":"https://doi.org/10.1145/1060745.1060762","title":"Thresher","display_name":"Thresher","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2138405339","doi":"https://doi.org/10.1145/1060745.1060762","mag":"2138405339"},"language":"en","primary_location":{"id":"doi:10.1145/1060745.1060762","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1060745.1060762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th international conference on World Wide Web  - WWW '05","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/A5024161800","display_name":"Andrew Hogue","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrew Hogue","raw_affiliation_strings":["Google Inc., New York, NY and MIT CSAIL, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Google Inc., New York, NY and MIT CSAIL, Cambridge, MA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028448267","display_name":"David R. Karger","orcid":"https://orcid.org/0000-0002-0024-5847"},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Karger","raw_affiliation_strings":["MIT CSAIL, Cambridge, MA","MIT - CSAIL, Cambridge, MA#TAB#"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL, Cambridge, MA","institution_ids":["https://openalex.org/I4210110987"]},{"raw_affiliation_string":"MIT - CSAIL, Cambridge, MA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5024161800"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":29.7944,"has_fulltext":false,"cited_by_count":134,"citation_normalized_percentile":{"value":0.99523952,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"86","last_page":"86"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9865999817848206,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9857000112533569,"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/haystack","display_name":"Haystack","score":0.8957091569900513},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8447557687759399},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.7418515682220459},{"id":"https://openalex.org/keywords/semantic-web-stack","display_name":"Semantic Web Stack","score":0.7017194628715515},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.593311071395874},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.587883472442627},{"id":"https://openalex.org/keywords/social-semantic-web","display_name":"Social Semantic Web","score":0.5847874283790588},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5128150582313538},{"id":"https://openalex.org/keywords/rdf","display_name":"RDF","score":0.4461718499660492},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.44605472683906555},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.43324416875839233},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.43148499727249146},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.23525387048721313}],"concepts":[{"id":"https://openalex.org/C13424479","wikidata":"https://www.wikidata.org/wiki/Q5687237","display_name":"Haystack","level":2,"score":0.8957091569900513},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8447557687759399},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7418515682220459},{"id":"https://openalex.org/C167379230","wikidata":"https://www.wikidata.org/wiki/Q1026884","display_name":"Semantic Web Stack","level":3,"score":0.7017194628715515},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.593311071395874},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.587883472442627},{"id":"https://openalex.org/C534406577","wikidata":"https://www.wikidata.org/wiki/Q7550843","display_name":"Social Semantic Web","level":3,"score":0.5847874283790588},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5128150582313538},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.4461718499660492},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.44605472683906555},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.43324416875839233},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.43148499727249146},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.23525387048721313}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1060745.1060762","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1060745.1060762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th international conference on World Wide Web  - WWW '05","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":17,"referenced_works":["https://openalex.org/W1485247436","https://openalex.org/W1536656120","https://openalex.org/W1553019137","https://openalex.org/W1560244990","https://openalex.org/W1568339100","https://openalex.org/W1569885000","https://openalex.org/W1603243937","https://openalex.org/W1975009259","https://openalex.org/W1979566122","https://openalex.org/W2090656662","https://openalex.org/W2110606473","https://openalex.org/W2129595335","https://openalex.org/W2145948275","https://openalex.org/W2153072229","https://openalex.org/W2169899598","https://openalex.org/W2912161846","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2069569467","https://openalex.org/W2349698472","https://openalex.org/W2038021528","https://openalex.org/W2048480329","https://openalex.org/W2363068772","https://openalex.org/W2183626957","https://openalex.org/W2378922560","https://openalex.org/W2059445287","https://openalex.org/W2388164838","https://openalex.org/W2561758991"],"abstract_inverted_index":{"We":[0,43],"describe":[1],"Thresher,":[2],"a":[3,36,59,100],"system":[4],"that":[5],"lets":[6],"non-technical":[7],"users":[8],"teach":[9],"their":[10,41,124],"browsers":[11],"how":[12],"to":[13,57,71,77,86,119,129],"extract":[14],"semantic":[15,30,95,102,109],"web":[16,37,96,106],"content":[17,31],"from":[18],"HTML":[19],"documents":[20,91],"on":[21,89],"the":[22,46,51,65,69,78,93,113,135],"World":[23],"Wide":[24],"Web.":[25],"Users":[26],"specify":[27],"examples":[28,56],"of":[29,54,80,134],"by":[32],"highlighting":[33],"them":[34],"in":[35,112],"browser":[38],"and":[39,67,75,122,132,138],"describing":[40],"meaning.":[42],"then":[44],"use":[45,133],"tree":[47],"edit":[48],"distance":[49],"between":[50],"DOM":[52],"subtrees":[53],"these":[55,81,87],"create":[58],"general":[60],"pattern,":[61],"or":[62],"wrapper,":[63],"for":[64],"content,":[66],"allow":[68],"user":[70],"bind":[72],"RDF":[73],"classes":[74],"predicates":[76],"nodes":[79],"wrappers.":[82],"By":[83,116],"overlaying":[84],"matches":[85],"patterns":[88],"standard":[90],"inside":[92],"Haystack":[94],"browser,":[97],"we":[98,127],"enable":[99],"rich":[101],"interaction":[103],"with":[104],"existing":[105],"pages,":[107],"\"unwrapping\"":[108],"data":[110],"buried":[111],"pages'":[114],"HTML.":[115],"allowing":[117],"end-users":[118],"create,":[120],"modify,":[121],"utilize":[123],"own":[125],"patterns,":[126],"hope":[128],"speed":[130],"adoption":[131],"Semantic":[136],"Web":[137],"its":[139],"applications.":[140]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
