{"id":"https://openalex.org/W939627119","doi":"https://doi.org/10.1007/978-3-319-13186-3_22","title":"Scalable Textual Similarity Search on Large Document Collections Through Random Indexing and K-means Clustering","display_name":"Scalable Textual Similarity Search on Large Document Collections Through Random Indexing and K-means Clustering","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W939627119","doi":"https://doi.org/10.1007/978-3-319-13186-3_22","mag":"939627119"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-13186-3_22","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-13186-3_22","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5089229841","display_name":"Ali Cevahir","orcid":null},"institutions":[{"id":"https://openalex.org/I1301041018","display_name":"Rakuten (Japan)","ror":"https://ror.org/0098kke80","country_code":"JP","type":"company","lineage":["https://openalex.org/I1301041018"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ali Cevahir","raw_affiliation_strings":["Rakuten Institute of Technology, Rakuten Inc., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Rakuten Institute of Technology, Rakuten Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I1301041018"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5089229841"],"corresponding_institution_ids":["https://openalex.org/I1301041018"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.0533,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.77478283,"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":"231","last_page":"238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","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/T10203","display_name":"Recommender Systems and Techniques","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/T11478","display_name":"Caching and Content Delivery","score":0.9983999729156494,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8700249791145325},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7839674949645996},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.7152443528175354},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6999326348304749},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6699023842811584},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6634848117828369},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.6066948175430298},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5653563737869263},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.5595077276229858},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5331332683563232},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5013787746429443},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.4857369065284729},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4855780005455017},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.47171467542648315},{"id":"https://openalex.org/keywords/full-text-search","display_name":"Full text search","score":0.4311603307723999},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24447011947631836},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2033482789993286},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20218294858932495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8700249791145325},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7839674949645996},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.7152443528175354},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6999326348304749},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6699023842811584},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6634848117828369},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.6066948175430298},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5653563737869263},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.5595077276229858},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5331332683563232},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5013787746429443},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.4857369065284729},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4855780005455017},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.47171467542648315},{"id":"https://openalex.org/C20228898","wikidata":"https://www.wikidata.org/wiki/Q83540","display_name":"Full text search","level":3,"score":0.4311603307723999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24447011947631836},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2033482789993286},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20218294858932495},{"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:10.1007/978-3-319-13186-3_22","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-13186-3_22","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W578653324","https://openalex.org/W1569487506","https://openalex.org/W1584739173","https://openalex.org/W1963535513","https://openalex.org/W1976618413","https://openalex.org/W2012483354","https://openalex.org/W2037757210","https://openalex.org/W2041836310","https://openalex.org/W2054141820","https://openalex.org/W2117354486","https://openalex.org/W2165612380","https://openalex.org/W2979473749","https://openalex.org/W3097609957"],"related_works":["https://openalex.org/W118734887","https://openalex.org/W2906958661","https://openalex.org/W2171572695","https://openalex.org/W2039742379","https://openalex.org/W2352030744","https://openalex.org/W2111281114","https://openalex.org/W2093377061","https://openalex.org/W2295679435","https://openalex.org/W2349570474","https://openalex.org/W2132792521"],"abstract_inverted_index":null,"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
