{"id":"https://openalex.org/W2114454131","doi":"https://doi.org/10.1145/1061811.1061816","title":"Extracting content from accessible web pages","display_name":"Extracting content from accessible web pages","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2114454131","doi":"https://doi.org/10.1145/1061811.1061816","mag":"2114454131"},"language":"en","primary_location":{"id":"doi:10.1145/1061811.1061816","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1061811.1061816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 International Cross-Disciplinary Workshop on Web Accessibility (W4A)  - W4A '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/A5064707257","display_name":"Suhit Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107408","display_name":"New York Proton Center","ror":"https://ror.org/01m7v2988","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210107408"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Suhit Gupta","raw_affiliation_strings":["New York, NY"],"affiliations":[{"raw_affiliation_string":"New York, NY","institution_ids":["https://openalex.org/I4210107408"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090171418","display_name":"Gail E. Kaiser","orcid":"https://orcid.org/0000-0002-8791-1178"},"institutions":[{"id":"https://openalex.org/I4210107408","display_name":"New York Proton Center","ror":"https://ror.org/01m7v2988","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210107408"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gail Kaiser","raw_affiliation_strings":["New York, NY"],"affiliations":[{"raw_affiliation_string":"New York, NY","institution_ids":["https://openalex.org/I4210107408"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5064707257"],"corresponding_institution_ids":["https://openalex.org/I4210107408"],"apc_list":null,"apc_paid":null,"fwci":10.1766,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.97747184,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"26","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"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":0.9993000030517578,"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/T12481","display_name":"Digital Accessibility for Disabilities","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/3307","display_name":"Human Factors and Ergonomics"},"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/T13629","display_name":"Text Readability and Simplification","score":0.9624000191688538,"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":0.8010567426681519},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7393751740455627},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7211185693740845},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.7156881093978882},{"id":"https://openalex.org/keywords/clutter","display_name":"Clutter","score":0.5905340909957886},{"id":"https://openalex.org/keywords/web-content","display_name":"Web content","score":0.586693525314331},{"id":"https://openalex.org/keywords/web-standards","display_name":"Web standards","score":0.5583427548408508},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.5537713766098022},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4798164367675781},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.4605952501296997},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3954537808895111}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8010567426681519},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7393751740455627},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7211185693740845},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7156881093978882},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.5905340909957886},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.586693525314331},{"id":"https://openalex.org/C182321512","wikidata":"https://www.wikidata.org/wiki/Q1153289","display_name":"Web standards","level":3,"score":0.5583427548408508},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.5537713766098022},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4798164367675781},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.4605952501296997},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3954537808895111},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1061811.1061816","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1061811.1061816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 International Cross-Disciplinary Workshop on Web Accessibility (W4A)  - W4A '05","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.60.357","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.60.357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arsky.com/WWW2005/WorkshopCD/workshop/wf01/26-Gupta.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2012575882","https://openalex.org/W2026642282","https://openalex.org/W2087406717","https://openalex.org/W2147466442","https://openalex.org/W2161261009"],"related_works":["https://openalex.org/W4309209857","https://openalex.org/W4322734464","https://openalex.org/W2264639909","https://openalex.org/W1971846537","https://openalex.org/W2121033530","https://openalex.org/W1604407927","https://openalex.org/W1963489897","https://openalex.org/W2159472163","https://openalex.org/W2140595478","https://openalex.org/W1933978566"],"abstract_inverted_index":{"Web":[0,39],"pages":[1,52,168,184],"often":[2],"contain":[3],"clutter":[4,90],"(such":[5],"as":[6,81,83,137],"ads,":[7],"unnecessary":[8],"animations":[9],"and":[10,33,196],"extraneous":[11],"links)":[12],"around":[13],"the":[14,89,104,110,128,153,174],"body":[15],"of":[16,47,72,101,106,112],"an":[17,69],"article,":[18],"which":[19],"distracts":[20],"a":[21,45,95,99,138],"user":[22],"from":[23,124,152],"actual":[24],"content.":[25],"This":[26,189],"can":[27],"be":[28,79],"especially":[29],"inconvenient":[30],"for":[31,59,109],"blind":[32],"visually":[34],"impaired":[35],"users.":[36],"The":[37],"W3C's":[38],"Accessibility":[40],"Initiative":[41],"(WAI)":[42],"has":[43,66],"defined":[44],"set":[46,71],"guidelines":[48],"to":[49,78,87,199],"make":[50],"web":[51,167,183,201],"more":[53,142],"compatible":[54],"with":[55,61,173],"tools":[56],"built":[57],"specifically":[58],"persons":[60],"disabilities.":[62],"While":[63],"this":[64],"initiative":[65],"put":[67],"forth":[68],"excellent":[70],"principles,":[73],"unfortunately":[74],"many":[75],"websites":[76,125],"continue":[77],"inaccessible":[80],"well":[82],"cluttered.":[84],"In":[85],"order":[86],"address":[88],"problem,":[91],"we":[92,157],"have":[93,163],"developed":[94],"framework":[96,195],"that":[97,118,131,160,169],"employs":[98],"host":[100],"heuristics":[102,146],"in":[103,135],"form":[105],"tunable":[107],"filters":[108],"purpose":[111],"content":[113,130,193],"extraction.":[114],"Our":[115],"hypothesis":[116],"is":[117],"automatically":[119],"filtering":[120],"out":[121],"selected":[122],"elements":[123],"will":[126],"leave":[127],"base":[129],"users":[132],"are":[133,147,170],"interested":[134],"and,":[136],"side-effect,":[139],"render":[140],"them":[141],"accessible.":[143],"Although":[144],"our":[145,192],"intuition-based,":[148],"rather":[149],"than":[150],"derived":[151],"W3C":[154],"accessibility":[155,175],"guidelines,":[156],"imagined":[158],"however":[159],"they":[161],"would":[162],"little":[164],"impact":[165],"on":[166],"fully":[171],"compliant":[172],"guidelines.":[176],"We":[177],"were":[178],"wrong:":[179],"some":[180],"(technically)":[181],"accessible":[182,200],"still":[185],"include":[186],"significant":[187],"clutter.":[188],"paper":[190],"discusses":[191],"extraction":[194],"its":[197],"application":[198],"pages.":[202]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
