{"id":"https://openalex.org/W2749612946","doi":"https://doi.org/10.1145/3132847.3133016","title":"Efficient Document Filtering Using Vector Space Topic Expansion and Pattern-Mining","display_name":"Efficient Document Filtering Using Vector Space Topic Expansion and Pattern-Mining","publication_year":2017,"publication_date":"2017-11-06","ids":{"openalex":"https://openalex.org/W2749612946","doi":"https://doi.org/10.1145/3132847.3133016","mag":"2749612946"},"language":"en","primary_location":{"id":"doi:10.1145/3132847.3133016","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3132847.3133016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/230205","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075249384","display_name":"Julia Proskurnia","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Julia Proskurnia","raw_affiliation_strings":["\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062619833","display_name":"Ruslan Mavlyutov","orcid":"https://orcid.org/0000-0001-8607-5828"},"institutions":[{"id":"https://openalex.org/I154338468","display_name":"University of Fribourg","ror":"https://ror.org/022fs9h90","country_code":"CH","type":"education","lineage":["https://openalex.org/I154338468"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ruslan Mavlyutov","raw_affiliation_strings":["University of Fribourg, Fribourg, Switzerland"],"affiliations":[{"raw_affiliation_string":"University of Fribourg, Fribourg, Switzerland","institution_ids":["https://openalex.org/I154338468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084282503","display_name":"Carlos Castillo","orcid":"https://orcid.org/0000-0003-4544-0416"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Carlos Castillo","raw_affiliation_strings":["Universitat Pompeu Fabra, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001443156","display_name":"Karl Aberer","orcid":"https://orcid.org/0000-0003-3005-7342"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Karl Aberer","raw_affiliation_strings":["\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028454093","display_name":"Philippe Cudr\u00e9-Mauroux","orcid":"https://orcid.org/0000-0003-2588-4212"},"institutions":[{"id":"https://openalex.org/I154338468","display_name":"University of Fribourg","ror":"https://ror.org/022fs9h90","country_code":"CH","type":"education","lineage":["https://openalex.org/I154338468"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Philippe Cudr\u00e9-Mauroux","raw_affiliation_strings":["University of Fribourg, Fribourg, Switzerland"],"affiliations":[{"raw_affiliation_string":"University of Fribourg, Fribourg, Switzerland","institution_ids":["https://openalex.org/I154338468"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5075249384"],"corresponding_institution_ids":["https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":3.5409,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.93999618,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"457","last_page":"466"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.998199999332428,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.998199999332428,"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":0.9980000257492065,"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/T11309","display_name":"Music and Audio Processing","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8358569145202637},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.719290018081665},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.648770809173584},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6168121099472046},{"id":"https://openalex.org/keywords/mainstream","display_name":"Mainstream","score":0.5610283017158508},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4758700728416443},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.46579086780548096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4645167887210846},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4609566032886505},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.43615949153900146},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36217331886291504},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33145207166671753},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2141267955303192}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8358569145202637},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.719290018081665},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.648770809173584},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6168121099472046},{"id":"https://openalex.org/C2777617010","wikidata":"https://www.wikidata.org/wiki/Q18957","display_name":"Mainstream","level":2,"score":0.5610283017158508},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4758700728416443},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.46579086780548096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4645167887210846},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4609566032886505},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.43615949153900146},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36217331886291504},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33145207166671753},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2141267955303192},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3132847.3133016","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3132847.3133016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:repositori.upf.edu:10230/37019","is_oa":false,"landing_page_url":"http://hdl.handle.net/10230/37019","pdf_url":null,"source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:infoscience.tind.io:230205","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/139693","pdf_url":"http://infoscience.epfl.ch/record/230205","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:230205","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/139693","pdf_url":"http://infoscience.epfl.ch/record/230205","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1093674026","display_name":null,"funder_award_id":"agreement","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G2503557059","display_name":null,"funder_award_id":"Sinergia Grant","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G2525484684","display_name":null,"funder_award_id":"Sinergia","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G4247904154","display_name":null,"funder_award_id":"European Research Council","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5462641174","display_name":"Evolutionary consequences of selfing in the freshwater snail Galba truncatula","funder_award_id":"68325","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G576637567","display_name":null,"funder_award_id":"147609","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G5861819811","display_name":"Principles of Graph Data Integration","funder_award_id":"683253","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8051717526","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2749612946.pdf","grobid_xml":"https://content.openalex.org/works/W2749612946.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W1982029265","https://openalex.org/W2166559705","https://openalex.org/W2998574808"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2377237701","https://openalex.org/W2360099860","https://openalex.org/W4323893170","https://openalex.org/W1583826057","https://openalex.org/W2352463596","https://openalex.org/W2380850119","https://openalex.org/W2101450440","https://openalex.org/W2383675217","https://openalex.org/W2122605835"],"abstract_inverted_index":{"Automatically":[0],"extracting":[1,87],"information":[2],"from":[3],"social":[4,10,24,39],"media":[5],"is":[6,12,41,142],"challenging":[7],"given":[8],"that":[9,80,92,167],"content":[11,40],"often":[13],"noisy,":[14],"ambiguous,":[15],"and":[16,52,106,121,126,144],"inconsistent.":[17],"However,":[18],"as":[19],"many":[20],"stories":[21],"break":[22],"on":[23,158],"channels":[25],"first":[26],"before":[27],"being":[28],"picked":[29],"up":[30],"by":[31,65,86],"mainstream":[32],"media,":[33],"developing":[34],"methods":[35],"to":[36,55,60,103,118],"better":[37],"handle":[38],"of":[42,69,76,89,109,150,162],"utmost":[43],"importance.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48],"propose":[49],"a":[50,61,66,159],"robust":[51],"effective":[53],"approach":[54,157],"automatically":[56],"identify":[57],"microposts":[58,79],"related":[59],"specific":[62],"topic":[63],"defined":[64],"small":[67,132],"sample":[68],"reference":[70,84],"documents.":[71],"Our":[72,140],"framework":[73],"extracts":[74],"clusters":[75,95],"semantically":[77],"similar":[78],"overlap":[81],"with":[82,131,147],"the":[83,110,114],"documents,":[85],"combinations":[88],"key":[90],"features":[91],"define":[93],"those":[94],"through":[96],"frequent":[97],"pattern":[98],"mining.":[99],"This":[100],"allows":[101],"us":[102],"construct":[104],"compact":[105],"interpretable":[107],"representations":[108],"topic,":[111],"dramatically":[112],"decreasing":[113],"computational":[115],"burden":[116],"compared":[117],"classical":[119],"clustering":[120],"k-NN-based":[122],"machine":[123],"learning":[124],"techniques":[125],"producing":[127],"highly-competitive":[128],"results":[129],"even":[130],"training":[133,138],"sets":[134,149],"(less":[135],"than":[136],"1'000":[137],"objects).":[139],"method":[141],"efficient":[143],"scales":[145],"gracefully":[146],"large":[148,160],"incoming":[151],"microposts.":[152],"We":[153],"experimentally":[154],"validate":[155],"our":[156],"corpus":[161],"over":[163],"60M":[164],"microposts,":[165],"showing":[166],"it":[168],"significantly":[169],"outperforms":[170],"state-of-the-art":[171],"techniques.":[172]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}
