{"id":"https://openalex.org/W2587727761","doi":"https://doi.org/10.1145/3022227.3022251","title":"Identifying major contents among web pages with search engine suggests by modeling topics","display_name":"Identifying major contents among web pages with search engine suggests by modeling topics","publication_year":2017,"publication_date":"2017-01-05","ids":{"openalex":"https://openalex.org/W2587727761","doi":"https://doi.org/10.1145/3022227.3022251","mag":"2587727761"},"language":"en","primary_location":{"id":"doi:10.1145/3022227.3022251","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3022227.3022251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication","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/A5101993842","display_name":"Chen Zhao","orcid":"https://orcid.org/0000-0003-4993-5416"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chen Zhao","raw_affiliation_strings":["University of Tsukuba, Tsukuba, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, JAPAN","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100325921","display_name":"Jiaqi Li","orcid":"https://orcid.org/0000-0001-6076-4350"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jiaqi Li","raw_affiliation_strings":["University of Tsukuba, Tsukuba, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, JAPAN","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012279831","display_name":"Tian Nie","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tian Nie","raw_affiliation_strings":["University of Tsukuba, Tsukuba, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, JAPAN","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069144085","display_name":"Yi Ding","orcid":"https://orcid.org/0000-0002-0010-8279"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yi Ding","raw_affiliation_strings":["University of Tsukuba, Tsukuba, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, JAPAN","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091155050","display_name":"Linghan Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Linghan Xu","raw_affiliation_strings":["University of Tsukuba, Tsukuba, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, JAPAN","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066456246","display_name":"Takehito Utsuro","orcid":"https://orcid.org/0000-0003-4072-1833"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takehito Utsuro","raw_affiliation_strings":["University of Tsukuba, Tsukuba, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, JAPAN","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110632437","display_name":"Yasuhide Kawada","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yasuhide Kawada","raw_affiliation_strings":["Logworks Co., Ltd., Tokyo JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Logworks Co., Ltd., Tokyo JAPAN","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045875579","display_name":"Noriko Kando","orcid":"https://orcid.org/0000-0002-2133-0215"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Noriko Kando","raw_affiliation_strings":["National Institute of Informatics, Tokyo, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, JAPAN","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9991000294685364,"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":0.9991000294685364,"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/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9951000213623047,"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/intuition","display_name":"Intuition","score":0.8270848989486694},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7696815729141235},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7376654148101807},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.7209315299987793},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6696484088897705},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5213495492935181},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.4866069555282593},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48378536105155945},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4525160789489746},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.4212574362754822},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.41913938522338867},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.17165198922157288},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1371360719203949}],"concepts":[{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.8270848989486694},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7696815729141235},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7376654148101807},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.7209315299987793},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6696484088897705},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5213495492935181},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.4866069555282593},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48378536105155945},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4525160789489746},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.4212574362754822},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.41913938522338867},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.17165198922157288},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1371360719203949},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3022227.3022251","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3022227.3022251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication","raw_type":"proceedings-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/W153866397","https://openalex.org/W184934546","https://openalex.org/W658295343","https://openalex.org/W1794807579","https://openalex.org/W1831355885","https://openalex.org/W1880262756","https://openalex.org/W2021153570","https://openalex.org/W2038043464","https://openalex.org/W2130324521","https://openalex.org/W2144100511","https://openalex.org/W2147946282","https://openalex.org/W2159426623","https://openalex.org/W2250533720","https://openalex.org/W2251582277","https://openalex.org/W6607661948","https://openalex.org/W6621984194","https://openalex.org/W6682044806"],"related_works":["https://openalex.org/W2100795943","https://openalex.org/W2419328283","https://openalex.org/W4300670877","https://openalex.org/W4387299695","https://openalex.org/W2296228743","https://openalex.org/W2143424418","https://openalex.org/W4367694439","https://openalex.org/W2997495867","https://openalex.org/W2377634017","https://openalex.org/W4385753583"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,34,46,51,61,100],"problem":[4],"of":[5,13,25,43,71,83],"identifying":[6],"irrelevant":[7],"items":[8],"from":[9,73],"a":[10,117],"small":[11,153],"set":[12],"similar":[14,109],"documents":[15,151],"using":[16,37],"Web":[17,26,29,96],"search":[18,30,84,102],"engine":[19,85],"suggests.":[20],"Specifically,":[21],"we":[22],"collected":[23,98],"volumes":[24],"pages":[27,44,67,97],"through":[28],"engines":[31],"and":[32,65,88,123],"inspected":[33],"page":[35,63],"contents":[36],"topic":[38,48,52],"models.":[39],"Among":[40],"each":[41],"cluster":[42,64],"sharing":[45],"same":[47,101],"indicated":[49],"by":[50,115],"model,":[53],"our":[54,79],"technique":[55],"discovers":[56],"potential":[57],"content":[58],"organization":[59],"in":[60,78,152],"current":[62],"identifies":[66],"that":[68,74,95,137],"are":[69,104],"out":[70],"focus":[72],"topic.":[75],"The":[76,92],"metrics":[77],"approach":[80],"mainly":[81],"consist":[82],"suggest":[86,138],"frequency":[87,139],"inter-document":[89,143],"similarity":[90,144],"measures.":[91],"intuition":[93,114],"is":[94,146],"via":[99],"queries":[103],"more":[105],"likely":[106],"to":[107],"share":[108],"contents.":[110],"We":[111],"verify":[112],"this":[113],"implementing":[116],"subtopic":[118],"based":[119],"document":[120],"selection":[121],"framework":[122],"making":[124],"quantitative":[125],"evaluation":[126,134],"against":[127],"human":[128],"made":[129],"labeled":[130],"data":[131,154],"sets.":[132],"Our":[133],"result":[135],"reveals":[136],"analysis":[140],"along":[141],"with":[142,156],"measure":[145],"effective":[147],"at":[148],"filtering":[149],"off-topic":[150],"sets":[155],"satisfactory":[157],"performance.":[158]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
