{"id":"https://openalex.org/W2068098316","doi":"https://doi.org/10.1145/1458082.1458317","title":"Evaluating topic models for information retrieval","display_name":"Evaluating topic models for information retrieval","publication_year":2008,"publication_date":"2008-10-26","ids":{"openalex":"https://openalex.org/W2068098316","doi":"https://doi.org/10.1145/1458082.1458317","mag":"2068098316"},"language":"en","primary_location":{"id":"doi:10.1145/1458082.1458317","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","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/A5087568641","display_name":"Yi Xing","orcid":"https://orcid.org/0000-0001-9257-7613"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xing Yi","raw_affiliation_strings":["University of Massachusetts, Amherst, Amherst, MA, USA","University Of Massachusetts Amherst, Amherst, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University Of Massachusetts Amherst, Amherst, MA, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034070218","display_name":"James Allan","orcid":"https://orcid.org/0000-0003-0132-5694"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Allan","raw_affiliation_strings":["University of Massachusetts, Amherst, Amherst, MA, USA","University Of Massachusetts Amherst, Amherst, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University Of Massachusetts Amherst, Amherst, MA, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5087568641"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":5.8539,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.9572318,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1431","last_page":"1432"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9991999864578247,"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/T11719","display_name":"Data Quality and Management","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.835311233997345},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.8139602541923523},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.730487048625946},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.634607195854187},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5121290683746338},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.4460182189941406},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4453175365924835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3821840286254883},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38091975450515747},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32472583651542664}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.835311233997345},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.8139602541923523},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.730487048625946},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.634607195854187},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5121290683746338},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.4460182189941406},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4453175365924835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3821840286254883},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38091975450515747},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32472583651542664},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1458082.1458317","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.366.7286","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.366.7286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://maroo.cs.umass.edu/pub/web/getpdf.php?id=807","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"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":9,"referenced_works":["https://openalex.org/W1880262756","https://openalex.org/W2042980227","https://openalex.org/W2106490775","https://openalex.org/W2107743791","https://openalex.org/W2130395434","https://openalex.org/W2169213601","https://openalex.org/W4233135949","https://openalex.org/W4237791300","https://openalex.org/W4246858749"],"related_works":["https://openalex.org/W1978572805","https://openalex.org/W2383807498","https://openalex.org/W1997992934","https://openalex.org/W1987225439","https://openalex.org/W4238188170","https://openalex.org/W1585007175","https://openalex.org/W2125114371","https://openalex.org/W2019977573","https://openalex.org/W2149980199","https://openalex.org/W3125766170"],"abstract_inverted_index":{"We":[0,17],"explore":[1],"the":[2,63],"utility":[3],"of":[4,7],"different":[5],"types":[6],"topic":[8,21,31,35,57,78,97],"models,":[9],"both":[10],"probabilistic":[11],"and":[12],"not,":[13],"for":[14,25,72,101],"retrieval":[15],"purposes.":[16],"show":[18],"that:":[19],"(1)":[20],"models":[22,32],"are":[23,66,99],"effective":[24,51],"document":[26],"smoothing;":[27],"(2)":[28],"more":[29],"elaborate":[30],"that":[33,93],"capture":[34],"dependencies":[36],"provide":[37],"no":[38],"additional":[39],"gains;":[40],"(3)":[41],"smoothing":[42,53],"documents":[43,48],"by":[44,55],"using":[45,56],"their":[46],"similar":[47],"is":[49],"as":[50,52],"them":[54],"models;":[58],"(4)":[59],"topics":[60],"discovered":[61],"on":[62,88],"whole":[64],"corpus":[65],"too":[67],"coarse-grained":[68],"to":[69,76,81,96],"be":[70],"useful":[71],"query":[73],"expansion.":[74],"Experiments":[75],"measure":[77],"models'":[79],"ability":[80],"predict":[82],"held-out":[83],"likelihood":[84],"confirm":[85],"past":[86],"results":[87],"small":[89],"corpora,":[90],"but":[91],"suggest":[92],"simple":[94],"approaches":[95],"model":[98],"better":[100],"large":[102],"corpora.":[103]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
