{"id":"https://openalex.org/W2163506984","doi":"https://doi.org/10.1145/1835449.1835586","title":"The impact of collection size on relevance and diversity","display_name":"The impact of collection size on relevance and diversity","publication_year":2010,"publication_date":"2010-07-19","ids":{"openalex":"https://openalex.org/W2163506984","doi":"https://doi.org/10.1145/1835449.1835586","mag":"2163506984"},"language":"en","primary_location":{"id":"doi:10.1145/1835449.1835586","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1835449.1835586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-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/A5067054454","display_name":"Marijn Koolen","orcid":"https://orcid.org/0000-0002-0301-2029"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Marijn Koolen","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044511901","display_name":"Jaap Kamps","orcid":"https://orcid.org/0000-0002-6614-0087"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jaap Kamps","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5067054454"],"corresponding_institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18358286,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"727","last_page":"728"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","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/T10286","display_name":"Information Retrieval and Search Behavior","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/T12016","display_name":"Web Data Mining and Analysis","score":0.9700999855995178,"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/T11161","display_name":"Consumer Market Behavior and Pricing","score":0.955299973487854,"subfield":{"id":"https://openalex.org/subfields/1406","display_name":"Marketing"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.7714803218841553},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6658221483230591},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.583124041557312},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5687735080718994},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.5197629332542419},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5049133896827698},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.43978071212768555},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33524924516677856},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.26125991344451904},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16158533096313477},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11228704452514648},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.08389279246330261}],"concepts":[{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7714803218841553},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6658221483230591},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.583124041557312},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5687735080718994},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.5197629332542419},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5049133896827698},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.43978071212768555},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33524924516677856},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.26125991344451904},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16158533096313477},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11228704452514648},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.08389279246330261},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1835449.1835586","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1835449.1835586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/e6ae5282-b4dd-4bb7-a771-553c9366f63c","is_oa":false,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/the-impact-of-collection-size-on-relevance-and-diversity(e6ae5282-b4dd-4bb7-a771-553c9366f63c).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Koolen, M & Kamps, J 2010, The impact of collection size on relevance and diversity. in H-H Chen, E N Efthimiadis, J Savoy, F Crestani & S Marchand-Maillet (eds), SIGIR 2010: proceedings: 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval: Geneva, Switzerland, July 19-23, 2010. Association for Computing Machinery, New York, NY, pp. 727-728, 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2010), Geneva, Switzerland, 19/07/10. https://doi.org/10.1145/1835449.1835586","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.184.7426","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.184.7426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://staff.science.uva.nl/%7Ekamps/publications/2010/kool%3Aimpa10.pdf","raw_type":"text"},{"id":"pmh:oai:dare.uva.nl:publications/e6ae5282-b4dd-4bb7-a771-553c9366f63c","is_oa":false,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/the-impact-of-collection-size-on-relevance-and-diversity(e6ae5282-b4dd-4bb7-a771-553c9366f63c).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Koolen, M & Kamps, J 2010, The impact of collection size on relevance and diversity. in H-H Chen, E N Efthimiadis, J Savoy, F Crestani & S Marchand-Maillet (eds), SIGIR 2010: proceedings: 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval: Geneva, Switzerland, July 19-23, 2010. Association for Computing Machinery, New York, NY, pp. 727-728, 33rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2010), Geneva, Switzerland, 19/07/10. https://doi.org/10.1145/1835449.1835586","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W94637519","https://openalex.org/W1518041103","https://openalex.org/W4399373782"],"related_works":["https://openalex.org/W2038179415","https://openalex.org/W2559401578","https://openalex.org/W1732921787","https://openalex.org/W2593073376","https://openalex.org/W2203635993","https://openalex.org/W1839203737","https://openalex.org/W3100081050","https://openalex.org/W2291038164","https://openalex.org/W1930722330","https://openalex.org/W1981493414","https://openalex.org/W3088985319","https://openalex.org/W2605615016","https://openalex.org/W2165862792","https://openalex.org/W2073140429","https://openalex.org/W1562192608"],"abstract_inverted_index":{"It":[0],"has":[1,34],"been":[2],"observed":[3],"that":[4,14],"precision":[5],"increases":[6],"with":[7],"collection":[8,71],"size.":[9],"One":[10],"explanation":[11],"could":[12],"be":[13],"the":[15,28,39,58,67,70,74,83],"redundancy":[16],"of":[17,50,57,69,78],"information":[18,41],"increases,":[19],"making":[20],"it":[21],"easier":[22],"to":[23],"find":[24],"multiple":[25,55],"documents":[26],"conveying":[27],"same":[29,40],"information.":[30],"Arguably,":[31],"a":[32,48],"user":[33],"no":[35],"interest":[36],"in":[37],"reading":[38],"over":[42],"and":[43,76],"over,":[44],"but":[45],"would":[46],"prefer":[47],"set":[49],"diverse":[51],"search":[52,59],"results":[53,80],"covering":[54],"aspects":[56],"topic.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64],"look":[65],"at":[66],"impact":[68],"size":[72],"on":[73],"relevance":[75],"diversity":[77],"retrieval":[79],"by":[81],"down-sampling":[82],"collection.":[84]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
