{"id":"https://openalex.org/W2067745404","doi":"https://doi.org/10.1080/13614560701478897","title":"Towards mining past content of Web pages","display_name":"Towards mining past content of Web pages","publication_year":2007,"publication_date":"2007-07-01","ids":{"openalex":"https://openalex.org/W2067745404","doi":"https://doi.org/10.1080/13614560701478897","mag":"2067745404"},"language":"en","primary_location":{"id":"doi:10.1080/13614560701478897","is_oa":false,"landing_page_url":"https://doi.org/10.1080/13614560701478897","pdf_url":null,"source":{"id":"https://openalex.org/S5817663","display_name":"New Review of Hypermedia and Multimedia","issn_l":"1361-4568","issn":["1361-4568","1740-7842"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"New Review of Hypermedia and Multimedia","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/A5079733597","display_name":"Adam Jatowt","orcid":"https://orcid.org/0000-0001-7235-0665"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"A. Jatowt","raw_affiliation_strings":["Kyoto University , Yoshida-Honmachi, Sakyo-ku, 606-8501, Kyoto, Japan","Kyoto University, Kyoto, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"Kyoto University , Yoshida-Honmachi, Sakyo-ku, 606-8501, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101943741","display_name":"Katsumi Tanaka","orcid":"https://orcid.org/0000-0003-1731-931X"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Tanaka","raw_affiliation_strings":["Kyoto University , Yoshida-Honmachi, Sakyo-ku, 606-8501, Kyoto, Japan","Kyoto University, Kyoto, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"Kyoto University , Yoshida-Honmachi, Sakyo-ku, 606-8501, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079733597"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":2.3736,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.91103567,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"13","issue":"1","first_page":"77","last_page":"86"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9972000122070312,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9797000288963318,"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":0.7542827725410461},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6064212918281555},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.5488725900650024},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.52097088098526},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.45588573813438416},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.42919737100601196},{"id":"https://openalex.org/keywords/web-content","display_name":"Web content","score":0.42265522480010986},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.36646533012390137},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.04394298791885376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7542827725410461},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6064212918281555},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.5488725900650024},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.52097088098526},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.45588573813438416},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.42919737100601196},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.42265522480010986},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36646533012390137},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.04394298791885376},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/13614560701478897","is_oa":false,"landing_page_url":"https://doi.org/10.1080/13614560701478897","pdf_url":null,"source":{"id":"https://openalex.org/S5817663","display_name":"New Review of Hypermedia and Multimedia","issn_l":"1361-4568","issn":["1361-4568","1740-7842"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"New Review of Hypermedia and Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W580036881","https://openalex.org/W1521478692","https://openalex.org/W1594112393","https://openalex.org/W1603595185","https://openalex.org/W1604798403","https://openalex.org/W1617287874","https://openalex.org/W2005492507","https://openalex.org/W2021314079","https://openalex.org/W2026642282","https://openalex.org/W2042676911","https://openalex.org/W2067879405","https://openalex.org/W2113889316","https://openalex.org/W2152505903","https://openalex.org/W2172279492","https://openalex.org/W2913520302","https://openalex.org/W2918757710","https://openalex.org/W4249960090"],"related_works":["https://openalex.org/W240673130","https://openalex.org/W2506608575","https://openalex.org/W1846563554","https://openalex.org/W2162600120","https://openalex.org/W1548492051","https://openalex.org/W2209162541","https://openalex.org/W2127067408","https://openalex.org/W2163588476","https://openalex.org/W1964025622","https://openalex.org/W1547794081"],"abstract_inverted_index":{"While":[0],"much":[1],"attention":[2],"has":[3],"recently":[4],"focused":[5],"on":[6],"preserving":[7],"the":[8,12,50],"past":[9],"content":[10,68],"of":[11,19,69],"Web,":[13],"there":[14],"is":[15],"still":[16],"a":[17],"lack":[18],"efficient":[20],"tools":[21],"for":[22,42],"utilizing":[23],"data":[24,33],"stored":[25],"in":[26],"Web":[27,29,55,70],"archives.":[28],"archives":[30],"constitute":[31],"large":[32],"sources":[34],"that":[35],"could":[36],"be":[37],"extensively":[38],"analysed":[39],"and":[40,65,72,80],"mined":[41],"knowledge":[43,76],"discovery.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48],"describe":[49,74],"issues":[51],"involved":[52],"with":[53],"mining":[54],"archive":[56],"data.":[57],"We":[58],"discuss":[59],"several":[60],"concepts":[61],"related":[62],"to":[63],"collecting":[64],"analysing":[66],"historical":[67],"pages":[71],"briefly":[73],"two":[75],"discovery":[77],"tasks\u2014temporal":[78],"summarization":[79],"object":[81],"history":[82],"detection.":[83]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
