{"id":"https://openalex.org/W1965698293","doi":"https://doi.org/10.1145/2339530.2339621","title":"Harnessing the wisdom of the crowds for accurate web page clipping","display_name":"Harnessing the wisdom of the crowds for accurate web page clipping","publication_year":2012,"publication_date":"2012-08-12","ids":{"openalex":"https://openalex.org/W1965698293","doi":"https://doi.org/10.1145/2339530.2339621","mag":"1965698293"},"language":"en","primary_location":{"id":"doi:10.1145/2339530.2339621","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2339530.2339621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100434052","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0003-4291-7952"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China",", University of Science and Technology of China, Hefei, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":", University of Science and Technology of China, Hefei, China#TAB#","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013689593","display_name":"Linpeng Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linpeng Tang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","[Shanghai Jiao Tong University, Shanghai, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"[Shanghai Jiao Tong University, Shanghai, China]","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100752685","display_name":"Ping Luo","orcid":"https://orcid.org/0000-0002-6645-4721"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ping Luo","raw_affiliation_strings":["HP Labs China, Beijing, China","HP Labs China Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Labs China, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"HP Labs China Beijing, China#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048237545","display_name":"Enhong Chen","orcid":"https://orcid.org/0000-0002-4835-4102"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enhong Chen","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China",", University of Science and Technology of China, Hefei, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":", University of Science and Technology of China, Hefei, China#TAB#","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076440257","display_name":"Limei Jiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Limei Jiao","raw_affiliation_strings":["HP Labs China, Beijing, China","HP Labs China Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Labs China, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"HP Labs China Beijing, China#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340891","display_name":"Min Wang","orcid":"https://orcid.org/0000-0002-1580-6387"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Wang","raw_affiliation_strings":["HP Labs China, Beijing, China","HP Labs China Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Labs China, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"HP Labs China Beijing, China#TAB#","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015586553","display_name":"Guiquan Liu","orcid":"https://orcid.org/0000-0003-0653-3935"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guiquan Liu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China",", University of Science and Technology of China, Hefei, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":", University of Science and Technology of China, Hefei, China#TAB#","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7207,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.66507712,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"570","last_page":"578"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9980000257492065,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9954000115394592,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8495875597000122},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.765021562576294},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6626695990562439},{"id":"https://openalex.org/keywords/database-transaction","display_name":"Database transaction","score":0.556917130947113},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.5212705135345459},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.4993577003479004},{"id":"https://openalex.org/keywords/page-view","display_name":"Page view","score":0.4833180904388428},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48234885931015015},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.44681835174560547},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4116847515106201},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3250964879989624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13775089383125305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8495875597000122},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.765021562576294},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6626695990562439},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.556917130947113},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.5212705135345459},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.4993577003479004},{"id":"https://openalex.org/C103645729","wikidata":"https://www.wikidata.org/wiki/Q911187","display_name":"Page view","level":5,"score":0.4833180904388428},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48234885931015015},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.44681835174560547},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4116847515106201},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3250964879989624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13775089383125305}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2339530.2339621","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2339530.2339621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.365.1552","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.365.1552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hpl.hp.com/people/ping_luo/kdd210-Lei.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1585646276","https://openalex.org/W1966102147","https://openalex.org/W1974000287","https://openalex.org/W1991565788","https://openalex.org/W2013203774","https://openalex.org/W2051141368","https://openalex.org/W2064853889","https://openalex.org/W2076665947","https://openalex.org/W2108560469","https://openalex.org/W2115482638","https://openalex.org/W2137012502","https://openalex.org/W2140208587","https://openalex.org/W2145076056","https://openalex.org/W2148693963","https://openalex.org/W2166559705","https://openalex.org/W4252403066","https://openalex.org/W4285719527","https://openalex.org/W6681989899"],"related_works":["https://openalex.org/W2055154498","https://openalex.org/W2051097555","https://openalex.org/W2045069236","https://openalex.org/W2136599613","https://openalex.org/W4230700435","https://openalex.org/W2542335678","https://openalex.org/W2074126298","https://openalex.org/W2087758976","https://openalex.org/W4237105987","https://openalex.org/W2492611973"],"abstract_inverted_index":{"Clipping":[0],"Web":[1,10,17,45,73,108,121,147,260],"pages,":[2,11,122],"namely":[3],"extracting":[4],"the":[5,64,93,96,113,138,168,173,178,193,206,223,230,240,243],"informative":[6,103],"clips":[7,104,139],"(areas)":[8],"from":[9,257],"has":[12],"many":[13,26],"applications,":[14],"such":[15],"as":[16,130],"printing":[18],"and":[19,49,123,217,262],"e-reading":[20],"on":[21,41,105,115,144,161,225,246,266],"small":[22],"handheld":[23],"devices.":[24],"Although":[25],"existing":[27],"methods":[28],"attempt":[29],"to":[30,98,214,227],"address":[31],"this":[32,86,89,124,165,183],"task,":[33],"most":[34],"of":[35,44,68,72,95,102,205,242,253],"them":[36],"can":[37,127],"either":[38],"work":[39],"only":[40,172],"certain":[42,146],"types":[43,71],"pages":[46,74,256],"(e.g.,":[47],"news-":[48],"blog-like":[50],"web":[51,255],"pages),":[52],"or":[53],"perform":[54],"semi-automatically":[55],"where":[56,134],"extra":[57],"user":[58,143],"efforts":[59],"are":[60],"required":[61],"in":[62,76,88,182,192],"adjusting":[63],"outputs.":[65],"The":[66],"problem":[67],"clipping":[69],"any":[70,106],"accurately":[75],"a":[77,131,142,145,152,202,247],"totally":[78],"automatic":[79],"way":[80],"remains":[81],"pretty":[82],"much":[83],"open.":[84],"To":[85],"end":[87],"study":[90],"we":[91,111,150,221,238],"harness":[92],"wisdom":[94],"crowds":[97],"provide":[99],"accurate":[100],"recommendation":[101,169],"given":[107],"pages.":[109],"Specifically,":[110],"leverage":[112],"knowledge":[114,125],"how":[116],"previous":[117],"users":[118],"clip":[119],"similar":[120],"repository":[126],"be":[128],"represented":[129],"transaction":[132,136,162],"database":[133,163],"each":[135],"contains":[137],"selected":[140],"by":[141],"page.":[148],"Then,":[149],"formulate":[151],"new":[153],"pattern":[154,174,179,235],"mining":[155,157],"problem,":[156],"top-1":[158],"qualified":[159],"pattern,":[160],"for":[164,233],"recommendation.":[166,219],"Here,":[167],"considers":[170],"not":[171],"support":[175,186],"but":[176],"also":[177],"occupancy":[180,197,226],"(proposed":[181],"work).":[184],"High":[185],"requires":[187,198],"that":[188,199],"patterns":[189,200],"appear":[190,209],"frequently":[191],"database,":[194],"while":[195],"high":[196],"occupy":[201],"large":[203,267],"portion":[204],"transactions":[207],"they":[208],"in.":[210],"Thus,":[211],"it":[212],"leads":[213],"both":[215],"precise":[216],"complete":[218],"Additionally,":[220],"explore":[222],"properties":[224],"further":[228],"prune":[229],"search":[231],"space":[232],"high-efficient":[234],"mining.":[236],"Finally,":[237],"show":[239],"effectiveness":[241],"proposed":[244],"algorithm":[245],"human-labeled":[248],"ground":[249],"truth":[250],"dataset":[251],"consisting":[252],"2000":[254],"100":[258],"major":[259],"sites,":[261],"demonstrate":[263],"its":[264],"efficiency":[265],"synthetic":[268],"datasets.":[269]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
