{"id":"https://openalex.org/W2957505564","doi":"https://doi.org/10.1145/3326457","title":"Constructing Novel Block Layouts for Webpage Analysis","display_name":"Constructing Novel Block Layouts for Webpage Analysis","publication_year":2019,"publication_date":"2019-07-10","ids":{"openalex":"https://openalex.org/W2957505564","doi":"https://doi.org/10.1145/3326457","mag":"2957505564"},"language":"en","primary_location":{"id":"doi:10.1145/3326457","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3326457","pdf_url":null,"source":{"id":"https://openalex.org/S97833917","display_name":"ACM Transactions on Internet Technology","issn_l":"1533-5399","issn":["1533-5399","1557-6051"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Internet Technology","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/A5032989000","display_name":"Zexun Jiang","orcid":"https://orcid.org/0000-0002-7905-7274"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zexun Jiang","raw_affiliation_strings":["Research Institute of Information Technology, Tsinghua University, Beijing, P. R. China"],"affiliations":[{"raw_affiliation_string":"Research Institute of Information Technology, Tsinghua University, Beijing, P. R. China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101469762","display_name":"Hao Yin","orcid":"https://orcid.org/0000-0002-7829-7196"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Yin","raw_affiliation_strings":["Research Institute of Information Technology, Tsinghua University, Beijing, P. R. China"],"affiliations":[{"raw_affiliation_string":"Research Institute of Information Technology, Tsinghua University, Beijing, P. R. China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004458037","display_name":"Yulei Wu","orcid":"https://orcid.org/0000-0003-0801-8443"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yulei Wu","raw_affiliation_strings":["Department of Computer Science, University of Exeter, Exeter, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Exeter, Exeter, United Kingdom","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071514960","display_name":"Yongqiang Lyu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqiang Lyu","raw_affiliation_strings":["Research Institute of Information Technology, Tsinghua University, Beijing, P. R. China"],"affiliations":[{"raw_affiliation_string":"Research Institute of Information Technology, Tsinghua University, Beijing, P. R. China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770003","display_name":"Geyong Min","orcid":"https://orcid.org/0000-0003-1395-7314"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Geyong Min","raw_affiliation_strings":["Department of Computer Science, University of Exeter, Exeter, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Exeter, Exeter, United Kingdom","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100437208","display_name":"Xu Zhang","orcid":"https://orcid.org/0000-0002-1882-736X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Zhang","raw_affiliation_strings":["School of Electronic Science and Engineering, Nanjing University, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5032989000"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.6783,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77519356,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"19","issue":"3","first_page":"1","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9984999895095825,"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":0.9984999895095825,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9589999914169312,"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/T13731","display_name":"Advanced Computing and Algorithms","score":0.955299973487854,"subfield":{"id":"https://openalex.org/subfields/3322","display_name":"Urban Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.8705083131790161},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8439326882362366},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.8188040256500244},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6586591601371765},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5562253594398499},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.535385012626648},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5250622630119324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41147133708000183},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37667107582092285},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.28520047664642334},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06393623352050781}],"concepts":[{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.8705083131790161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8439326882362366},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8188040256500244},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6586591601371765},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5562253594398499},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.535385012626648},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5250622630119324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41147133708000183},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37667107582092285},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.28520047664642334},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06393623352050781},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3326457","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3326457","pdf_url":null,"source":{"id":"https://openalex.org/S97833917","display_name":"ACM Transactions on Internet Technology","issn_l":"1533-5399","issn":["1533-5399","1557-6051"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Internet Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1673310716","https://openalex.org/W1872023060","https://openalex.org/W2012575882","https://openalex.org/W2019577381","https://openalex.org/W2020254000","https://openalex.org/W2033403400","https://openalex.org/W2040075907","https://openalex.org/W2072489225","https://openalex.org/W2084358158","https://openalex.org/W2095289676","https://openalex.org/W2101909884","https://openalex.org/W2135769635","https://openalex.org/W2147428516","https://openalex.org/W2151265933","https://openalex.org/W2154484245","https://openalex.org/W2562836854","https://openalex.org/W2588006593","https://openalex.org/W2766818108","https://openalex.org/W2801141651","https://openalex.org/W2804434745","https://openalex.org/W3001494301","https://openalex.org/W3105265400","https://openalex.org/W4235169531"],"related_works":["https://openalex.org/W2592395359","https://openalex.org/W2045342254","https://openalex.org/W2535231171","https://openalex.org/W1501331687","https://openalex.org/W4255512592","https://openalex.org/W2501551404","https://openalex.org/W2326647871","https://openalex.org/W4205247302","https://openalex.org/W2468652214","https://openalex.org/W1504527458"],"abstract_inverted_index":{"Webpage":[0],"segmentation":[1,46,114,135],"is":[2],"the":[3,37,57,70,73,86,104,125,142,147,151],"basic":[4],"building":[5],"block":[6,94],"for":[7],"a":[8,44,60,65,92],"wide":[9],"range":[10],"of":[11,18,39,56,72,124,150,155],"webpage":[12,40,113,134],"analysis":[13],"methods.":[14,136],"The":[15,120,137],"rapid":[16],"development":[17],"Web":[19],"technologies":[20],"results":[21,139],"in":[22,85,103,153],"more":[23],"dynamic":[24,118],"and":[25,53,82,89,100,117,122,159],"complex":[26],"webpages,":[27],"which":[28],"bring":[29],"new":[30,66],"challenges":[31],"to":[32,68],"this":[33],"area.":[34],"To":[35],"improve":[36],"performance":[38,121],"segmentation,":[41],"we":[42,63,90],"propose":[43,91],"two-stage":[45,108],"method":[47,96,109,126,144],"that":[48,141],"can":[49,110],"combine":[50],"visual,":[51],"logic,":[52],"semantic":[54,98],"features":[55],"contents":[58],"on":[59,75,78,115],"webpage.":[61],"Specifically,":[62],"devise":[64],"model":[67],"measure":[69],"similarities":[71],"elements":[74],"webpages":[76],"based":[77],"both":[79],"visual":[80,101],"layout":[81],"logic":[83],"organization":[84],"first":[87],"stage,":[88],"novel":[93],"regrouping":[95],"using":[97],"statistics":[99],"positions":[102],"second":[105],"stage.":[106],"This":[107],"effectively":[111],"conduct":[112],"complicated":[116],"webpages.":[119],"accuracy":[123],"are":[127],"verified":[128],"by":[129],"comparing":[130],"with":[131],"two":[132],"existing":[133,148],"experiment":[138],"show":[140],"proposed":[143],"significantly":[145],"outperforms":[146],"state":[149],"art":[152],"terms":[154],"higher":[156],"precision,":[157],"recall,":[158],"accuracy.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
