{"id":"https://openalex.org/W2012588907","doi":"https://doi.org/10.1145/1410140.1410143","title":"Aggregate documents","display_name":"Aggregate documents","publication_year":2008,"publication_date":"2008-09-16","ids":{"openalex":"https://openalex.org/W2012588907","doi":"https://doi.org/10.1145/1410140.1410143","mag":"2012588907"},"language":"en","primary_location":{"id":"doi:10.1145/1410140.1410143","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1410140.1410143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eighth ACM symposium on Document engineering","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/A5083137668","display_name":"Michael Shilman","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Michael Shilman","raw_affiliation_strings":["Wize.com, San Mateo, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wize.com, San Mateo, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5083137668"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5072,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.59207717,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"7"},"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/T12478","display_name":"Wikis in Education and Collaboration","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9546999931335449,"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/computer-science","display_name":"Computer science","score":0.7318885922431946},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6613536477088928},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.6318784952163696},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6147909164428711},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5282261371612549},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5192089676856995},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.508363664150238},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3826218545436859},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37938088178634644},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.0721084475517273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7318885922431946},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6613536477088928},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.6318784952163696},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6147909164428711},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5282261371612549},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5192089676856995},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.508363664150238},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3826218545436859},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37938088178634644},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0721084475517273},{"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1410140.1410143","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1410140.1410143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eighth ACM symposium on Document engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1487429615","https://openalex.org/W1607783759","https://openalex.org/W1613836731"],"related_works":["https://openalex.org/W2370205415","https://openalex.org/W4387493491","https://openalex.org/W2904225411","https://openalex.org/W4388331409","https://openalex.org/W2485872624","https://openalex.org/W2169921015","https://openalex.org/W2651370314","https://openalex.org/W1961128080","https://openalex.org/W2323686453","https://openalex.org/W2632043587"],"abstract_inverted_index":{"With":[0],"the":[1,13,32,87,91,133],"dramatic":[2],"increase":[3],"in":[4,12,76],"quantity":[5],"and":[6,59,68,84,110,138,153],"diversity":[7],"of":[8,15,26,34,62,89,120,148],"online":[9],"content,":[10,18],"particularly":[11],"form":[14],"user":[16],"generated":[17],"we":[19],"now":[20,51],"have":[21],"access":[22],"to":[23,44,72,105,123],"unprecedented":[24],"amounts":[25],"information.":[27],"Whether":[28],"you":[29],"are":[30,50],"researching":[31],"purchase":[33],"a":[35,40,46,97,117,130,145,151],"new":[36],"cell":[37],"phone,":[38],"planning":[39],"vacation,":[41],"or":[42],"trying":[43],"assess":[45,73],"political":[47],"candidate,":[48],"there":[49],"countless":[52,94],"resources":[53],"at":[54],"your":[55],"fingertips.":[56],"However,":[57],"finding":[58],"making":[60],"sense":[61],"all":[63],"this":[64,113],"information":[65,92],"is":[66,70,78,102,108],"laborious":[67],"it":[69,101],"difficult":[71],"high-level":[74],"trends":[75],"what":[77,107],"said.":[79],"Web":[80],"sites":[81],"like":[82],"Wikipedia":[83],"Digg":[85],"democratize":[86],"process":[88],"organizing":[90],"from":[93],"document":[95],"into":[96,150],"single":[98],"source":[99],"where":[100],"somewhat":[103],"easier":[104],"understand":[106],"important":[109],"interesting.":[111],"In":[112],"talk,":[114],"I":[115],"describe":[116],"complementary":[118],"set":[119,147],"automated":[121],"alternatives":[122],"these":[124,127],"approaches,":[125],"demonstrate":[126],"approaches":[128],"with":[129],"working":[131],"example,":[132],"commercial":[134],"web":[135],"site":[136],"Wize.com,":[137],"derive":[139],"some":[140],"basic":[141],"principles":[142],"for":[143],"aggregating":[144],"diverse":[146],"documents":[149],"coherent":[152],"useful":[154],"summary.":[155]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
