{"id":"https://openalex.org/W2132480243","doi":"https://doi.org/10.1145/1166160.1166213","title":"The portrait of a common HTML web page","display_name":"The portrait of a common HTML web page","publication_year":2006,"publication_date":"2006-10-10","ids":{"openalex":"https://openalex.org/W2132480243","doi":"https://doi.org/10.1145/1166160.1166213","mag":"2132480243"},"language":"en","primary_location":{"id":"doi:10.1145/1166160.1166213","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1166160.1166213","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM symposium on Document engineering","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/A5084833276","display_name":"Ryan Levering","orcid":null},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ryan Levering","raw_affiliation_strings":["SUNY at Binghamton"],"affiliations":[{"raw_affiliation_string":"SUNY at Binghamton","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015386539","display_name":"Michal Cutler","orcid":null},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michal Cutler","raw_affiliation_strings":["SUNY at Binghamton"],"affiliations":[{"raw_affiliation_string":"SUNY at Binghamton","institution_ids":["https://openalex.org/I123946342"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5084833276"],"corresponding_institution_ids":["https://openalex.org/I123946342"],"apc_list":null,"apc_paid":null,"fwci":15.4916,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.98640672,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"198","last_page":"204"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9674000144004822,"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"}},{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9506999850273132,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/web-page","display_name":"Web page","score":0.8008110523223877},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7546606063842773},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.6785454154014587},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.6535517573356628},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.63299959897995},{"id":"https://openalex.org/keywords/html","display_name":"HTML","score":0.515021800994873},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4747759997844696},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.4726385474205017},{"id":"https://openalex.org/keywords/page-view","display_name":"Page view","score":0.42559871077537537},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.3270120918750763}],"concepts":[{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.8008110523223877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7546606063842773},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.6785454154014587},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.6535517573356628},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.63299959897995},{"id":"https://openalex.org/C138708601","wikidata":"https://www.wikidata.org/wiki/Q8811","display_name":"HTML","level":3,"score":0.515021800994873},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4747759997844696},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.4726385474205017},{"id":"https://openalex.org/C103645729","wikidata":"https://www.wikidata.org/wiki/Q911187","display_name":"Page view","level":5,"score":0.42559871077537537},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.3270120918750763},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1166160.1166213","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1166160.1166213","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM symposium on Document engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.518.2280","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.518.2280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://webseer.sourceforge.net/papers/doceng06.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1605217017","https://openalex.org/W2015933107","https://openalex.org/W2066055909","https://openalex.org/W2100589670","https://openalex.org/W2117209866","https://openalex.org/W2117850397","https://openalex.org/W2121871415","https://openalex.org/W2128341918","https://openalex.org/W2138621811","https://openalex.org/W2167859982","https://openalex.org/W2169557227"],"related_works":["https://openalex.org/W2277785728","https://openalex.org/W2389737178","https://openalex.org/W2003689064","https://openalex.org/W2489312077","https://openalex.org/W1488511360","https://openalex.org/W2120930843","https://openalex.org/W3025289787","https://openalex.org/W406631474","https://openalex.org/W2134450361","https://openalex.org/W2591821839"],"abstract_inverted_index":{"Web":[0],"pages":[1,50,155],"are":[2,7,57,103,157],"not":[3,17],"purely":[4],"text,":[5],"nor":[6],"they":[8],"solely":[9],"HTML.":[10],"This":[11,119],"paper":[12],"surveys":[13],"HTML":[14],"web":[15,49,69,154],"pages;":[16],"only":[18],"on":[19,26,44,68],"textual":[20],"content,":[21],"but":[22],"with":[23,37],"an":[24,38],"emphasis":[25],"higher":[27],"order":[28],"visual":[29,96],"features":[30],"and":[31,64,90,126,130,142,151],"supplementary":[32],"technology.":[33],"Using":[34],"a":[35,45,75,107,121,140],"crawler":[36],"in-house":[39],"developed":[40],"rendering":[41],"engine,":[42],"data":[43],"pseudo-random":[46],"sample":[47],"of":[48,80,83,94,101,110,128],"is":[51,117],"collected.":[52],"First,":[53],"several":[54],"basic":[55],"attributes":[56],"collected":[58],"to":[59,161],"verify":[60],"the":[61,78,111,115,124,146,162],"collection":[62],"process":[63],"confirm":[65],"certain":[66],"assumptions":[67],"page":[70,84,137],"text.":[71],"Next,":[72],"we":[73],"take":[74],"look":[76,122],"at":[77,123],"distribution":[79],"different":[81,99],"types":[82,100],"content":[85,102,116],"(text,":[86],"images,":[87],"plug-in":[88],"objects,":[89],"forms)":[91],"in":[92,113,145],"terms":[93],"rendered":[95],"area.":[97],"Those":[98],"broken":[104],"down":[105],"into":[106],"detailed":[108],"view":[109],"ways":[112],"which":[114],"used.":[118],"includes":[120],"prevalence":[125],"usage":[127],"scripts":[129],"styles.":[131],"We":[132],"conclude":[133],"that":[134,156],"more":[135],"complex":[136],"elements":[138],"play":[139],"significant":[141],"underestimated":[143],"role":[144],"visually":[147],"attractive,":[148],"media":[149],"rich,":[150],"highly":[152],"interactive":[153],"currently":[158],"being":[159],"added":[160],"World":[163],"Wide":[164],"Web.":[165]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
