{"id":"https://openalex.org/W2012299268","doi":"https://doi.org/10.1016/0169-7552(96)00064-5","title":"An investigation of documents from the World Wide Web","display_name":"An investigation of documents from the World Wide Web","publication_year":1996,"publication_date":"1996-05-01","ids":{"openalex":"https://openalex.org/W2012299268","doi":"https://doi.org/10.1016/0169-7552(96)00064-5","mag":"2012299268"},"language":"en","primary_location":{"id":"doi:10.1016/0169-7552(96)00064-5","is_oa":false,"landing_page_url":"https://doi.org/10.1016/0169-7552(96)00064-5","pdf_url":null,"source":{"id":"https://openalex.org/S3084184","display_name":"Computer Networks and ISDN Systems","issn_l":"0169-7552","issn":["0169-7552","1879-2324"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Networks and ISDN Systems","raw_type":"journal-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/A5045188560","display_name":"Allison Woodruff","orcid":"https://orcid.org/0000-0002-5745-7103"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Allison Woodruff","raw_affiliation_strings":["Computer Science Division, University of California, Berkeley, CA 94720-1776, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Division, University of California, Berkeley, CA 94720-1776, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085311483","display_name":"Paul M. Aoki","orcid":"https://orcid.org/0000-0002-2311-4241"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul M. Aoki","raw_affiliation_strings":["Computer Science Division, University of California, Berkeley, CA 94720-1776, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Division, University of California, Berkeley, CA 94720-1776, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Eric Brewer","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Brewer","raw_affiliation_strings":["Computer Science Division, University of California, Berkeley, CA 94720-1776, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Division, University of California, Berkeley, CA 94720-1776, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013920584","display_name":"P. M. Gauthier","orcid":"https://orcid.org/0000-0002-3220-0432"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Gauthier","raw_affiliation_strings":["Computer Science Division, University of California, Berkeley, CA 94720-1776, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Division, University of California, Berkeley, CA 94720-1776, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113735960","display_name":"Lawrence A. Rowe","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lawrence A. Rowe","raw_affiliation_strings":["Computer Science Division, University of California, Berkeley, CA 94720-1776, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Division, University of California, Berkeley, CA 94720-1776, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5045188560"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":23.3458,"has_fulltext":false,"cited_by_count":88,"citation_normalized_percentile":{"value":0.99244768,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"28","issue":"7-11","first_page":"963","last_page":"980"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9991999864578247,"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":0.9991999864578247,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9825000166893005,"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/T13629","display_name":"Text Readability and Simplification","score":0.9815000295639038,"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":0.8813853859901428},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6291577816009521},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.5938694477081299},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.5921051502227783},{"id":"https://openalex.org/keywords/html-element","display_name":"HTML element","score":0.5528577566146851},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.55026775598526},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.5090495944023132},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44575878977775574},{"id":"https://openalex.org/keywords/file-size","display_name":"File size","score":0.41832488775253296},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.3789516091346741},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.11355626583099365},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08510342240333557}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8813853859901428},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6291577816009521},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.5938694477081299},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.5921051502227783},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.5528577566146851},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.55026775598526},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.5090495944023132},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44575878977775574},{"id":"https://openalex.org/C2776029614","wikidata":"https://www.wikidata.org/wiki/Q1146367","display_name":"File size","level":2,"score":0.41832488775253296},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.3789516091346741},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.11355626583099365},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08510342240333557},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1016/0169-7552(96)00064-5","is_oa":false,"landing_page_url":"https://doi.org/10.1016/0169-7552(96)00064-5","pdf_url":null,"source":{"id":"https://openalex.org/S3084184","display_name":"Computer Networks and ISDN Systems","issn_l":"0169-7552","issn":["0169-7552","1879-2324"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Networks and ISDN Systems","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.173.8263","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.173.8263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.ischool.utexas.edu/~i385df04/readings/woodruff(1996)-investigation.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.44.2493","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.44.2493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://epoch.cs.berkeley.edu:8000/~aoki/papers/www5-color.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.72.5840","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.72.5840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2.parc.com/istl/projects/uir/publications/items/UIR-1996-21-Woodruff-WWW5-WWW.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":11,"referenced_works":["https://openalex.org/W1955828503","https://openalex.org/W1982896842","https://openalex.org/W2009172590","https://openalex.org/W2021518417","https://openalex.org/W2037498077","https://openalex.org/W2061901927","https://openalex.org/W2074328307","https://openalex.org/W2621202400","https://openalex.org/W6646125113","https://openalex.org/W6652375896","https://openalex.org/W6655918061"],"related_works":["https://openalex.org/W4385695127","https://openalex.org/W2389761961","https://openalex.org/W4254300012","https://openalex.org/W2963706618","https://openalex.org/W2113184419","https://openalex.org/W1999548128","https://openalex.org/W2102475112","https://openalex.org/W2323786540","https://openalex.org/W2142681129","https://openalex.org/W1656419755"],"abstract_inverted_index":null,"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
