{"id":"https://openalex.org/W2095371587","doi":"https://doi.org/10.1145/2212776.2223695","title":"A platform for large-scale machine learning on web design","display_name":"A platform for large-scale machine learning on web design","publication_year":2012,"publication_date":"2012-05-05","ids":{"openalex":"https://openalex.org/W2095371587","doi":"https://doi.org/10.1145/2212776.2223695","mag":"2095371587"},"language":"en","primary_location":{"id":"doi:10.1145/2212776.2223695","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2212776.2223695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CHI '12 Extended Abstracts on Human Factors in Computing Systems","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/A5077783676","display_name":"Arvind Satyanarayan","orcid":"https://orcid.org/0000-0001-5564-635X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arvind Satyanarayan","raw_affiliation_strings":["Stanford University, Stanford, California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, California, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060597276","display_name":"Maxine Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maxine Lim","raw_affiliation_strings":["Stanford University, Stanford, California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, California, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023550565","display_name":"Scott Klemmer","orcid":"https://orcid.org/0000-0001-9006-0805"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Klemmer","raw_affiliation_strings":["Stanford University, Stanford, California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, California, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7349,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.82563005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1697","last_page":"1702"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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":0.9751999974250793,"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/T12285","display_name":"Surface Chemistry and Catalysis","score":0.9624000191688538,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8136996030807495},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.739752471446991},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6070923209190369},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.583584189414978},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.5593887567520142},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.47932350635528564},{"id":"https://openalex.org/keywords/web-design","display_name":"Web design","score":0.47785088419914246},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.47757723927497864},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4440314471721649},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3233300447463989},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0828094482421875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8136996030807495},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.739752471446991},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6070923209190369},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.583584189414978},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.5593887567520142},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.47932350635528564},{"id":"https://openalex.org/C521306242","wikidata":"https://www.wikidata.org/wiki/Q190637","display_name":"Web design","level":3,"score":0.47785088419914246},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.47757723927497864},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4440314471721649},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3233300447463989},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0828094482421875},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2212776.2223695","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2212776.2223695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CHI '12 Extended Abstracts on Human Factors in Computing Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.352.4563","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.352.4563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arvindsatya.com/papers/chi2012.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W608337257","https://openalex.org/W1556347322","https://openalex.org/W1613836731","https://openalex.org/W2075779758","https://openalex.org/W2117209866","https://openalex.org/W2126135370","https://openalex.org/W2154583606"],"related_works":["https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W4385695127","https://openalex.org/W2120222276","https://openalex.org/W3025289787","https://openalex.org/W2137912379","https://openalex.org/W1986474863","https://openalex.org/W2036104219"],"abstract_inverted_index":{"The":[0],"Web":[1,23,78,84],"is":[2],"an":[3,111],"enormous":[4],"and":[5,38,86,91,95,110],"diverse":[6],"repository":[7],"of":[8,40,82,98],"design":[9,24,61],"examples.":[10],"Although":[11],"people":[12],"often":[13],"draw":[14],"from":[15],"extant":[16],"designs":[17],"to":[18,51,89],"create":[19],"new":[20],"ones,":[21],"existing":[22],"tools":[25],"do":[26,44],"not":[27],"facilitate":[28],"example":[29],"reuse":[30],"in":[31],"a":[32,68,83,93,101,106],"way":[33],"that":[34,104],"captures":[35],"the":[36,41,60,99,115],"scale":[37],"diversity":[39],"Web.":[42],"To":[43],"so":[45],"requires":[46],"using":[47],"machine":[48,75],"learning":[49,76],"techniques":[50],"train":[52],"computational":[53],"models":[54],"which":[55,80],"can":[56],"be":[57],"queried":[58],"during":[59],"process.":[62],"In":[63],"this":[64],"work-in-progress,":[65],"we":[66],"present":[67],"platform":[69],"necessary":[70],"for":[71,113],"doing":[72],"such":[73],"large-scale":[74],"on":[77],"designs,":[79],"consists":[81],"crawler":[85],"proxy":[87],"server":[88],"harvest":[90],"store":[92],"lossless":[94],"immutable":[96],"snapshot":[97],"Web;":[100],"page":[102],"segmenter":[103],"codifies":[105],"page's":[107],"visual":[108],"layout;":[109],"interface":[112],"augmenting":[114],"segmentations":[116],"with":[117],"crowdsourced":[118],"metadata.":[119]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
