{"id":"https://openalex.org/W2137644567","doi":"https://doi.org/10.1145/2783258.2783411","title":"Dirichlet-Hawkes Processes with Applications to Clustering Continuous-Time Document Streams","display_name":"Dirichlet-Hawkes Processes with Applications to Clustering Continuous-Time Document Streams","publication_year":2015,"publication_date":"2015-08-07","ids":{"openalex":"https://openalex.org/W2137644567","doi":"https://doi.org/10.1145/2783258.2783411","mag":"2137644567"},"language":"en","primary_location":{"id":"doi:10.1145/2783258.2783411","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2783258.2783411","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2783411&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=2783411&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100721790","display_name":"Nan Du","orcid":"https://orcid.org/0000-0003-2855-7452"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nan Du","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, USA","[Georgia Institute of Technology, Atlanta, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"[Georgia Institute of Technology, Atlanta, USA]","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050499655","display_name":"Mehrdad Farajtabar","orcid":"https://orcid.org/0000-0002-5510-518X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehrdad Farajtabar","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, USA","[Georgia Institute of Technology, Atlanta, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"[Georgia Institute of Technology, Atlanta, USA]","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009154893","display_name":"Amr Ahmed","orcid":"https://orcid.org/0000-0002-7749-7911"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amr Ahmed","raw_affiliation_strings":["Google Strategic Technologies, Mountain View, USA","Google Strategic Technologies, Mountain View, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Strategic Technologies, Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Strategic Technologies, Mountain View, USA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000245150","display_name":"Alexander J. Smola","orcid":"https://orcid.org/0000-0002-7963-4721"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander J. Smola","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102898115","display_name":"Le Song","orcid":"https://orcid.org/0000-0003-0345-9899"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Le Song","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, USA","[Georgia Institute of Technology, Atlanta, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"[Georgia Institute of Technology, Atlanta, USA]","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":137,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"219","last_page":"228"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9991999864578247,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9991999864578247,"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/T13187","display_name":"Diffusion and Search Dynamics","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11830","display_name":"Point processes and geometric inequalities","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/2604","display_name":"Applied Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.8827617168426514},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7805320024490356},{"id":"https://openalex.org/keywords/hierarchical-dirichlet-process","display_name":"Hierarchical Dirichlet process","score":0.7431130409240723},{"id":"https://openalex.org/keywords/point-process","display_name":"Point process","score":0.682475745677948},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.677760660648346},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6658605337142944},{"id":"https://openalex.org/keywords/dirichlet-process","display_name":"Dirichlet process","score":0.636172354221344},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6207118630409241},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.6125611662864685},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.46577948331832886},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41659754514694214},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4146488308906555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32982203364372253},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.1286206841468811},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09865328669548035},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07724669575691223}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.8827617168426514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7805320024490356},{"id":"https://openalex.org/C141318989","wikidata":"https://www.wikidata.org/wiki/Q5753066","display_name":"Hierarchical Dirichlet process","level":4,"score":0.7431130409240723},{"id":"https://openalex.org/C88871306","wikidata":"https://www.wikidata.org/wiki/Q7208287","display_name":"Point process","level":2,"score":0.682475745677948},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.677760660648346},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6658605337142944},{"id":"https://openalex.org/C2781280628","wikidata":"https://www.wikidata.org/wiki/Q5280766","display_name":"Dirichlet process","level":3,"score":0.636172354221344},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6207118630409241},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.6125611662864685},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.46577948331832886},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41659754514694214},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4146488308906555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32982203364372253},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.1286206841468811},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09865328669548035},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07724669575691223},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2783258.2783411","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2783258.2783411","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2783411&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1003.3991","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1003.3991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cc.gatech.edu/%7Endu8/pdf/DuFarAmrSmoSon-KDD-2015.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1009.2815","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1009.2815","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cc.gatech.edu/%7Elsong/papers/DuFarAhmSmoSon15.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.726.9711","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.726.9711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cc.gatech.edu/%7Emfarajta/resources/Dirichlet-Hawkes.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/2783258.2783411","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2783258.2783411","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2783411&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1309293717","display_name":null,"funder_award_id":"BIGDATA 1R01GM108341","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4606317253","display_name":null,"funder_award_id":"IIS-1116886","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4715344146","display_name":"III: Small: Exploring Social and Behavioral Contexts for Information Retrieval","funder_award_id":"1116886","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7312543413","display_name":"CAREER: New Representations of Probability Distributions to Improve Machine Learning --- A Unified Kernel Embedding Framework for Distributions","funder_award_id":"1350983","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/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2137644567.pdf","grobid_xml":"https://content.openalex.org/works/W2137644567.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W43029633","https://openalex.org/W188609219","https://openalex.org/W258053484","https://openalex.org/W412511134","https://openalex.org/W645058498","https://openalex.org/W748467075","https://openalex.org/W1483307070","https://openalex.org/W1967687583","https://openalex.org/W1972882261","https://openalex.org/W2052197092","https://openalex.org/W2069849731","https://openalex.org/W2072644219","https://openalex.org/W2096765155","https://openalex.org/W2101645017","https://openalex.org/W2104827998","https://openalex.org/W2119148740","https://openalex.org/W2142880609","https://openalex.org/W2149020252","https://openalex.org/W2154099718","https://openalex.org/W2157991246","https://openalex.org/W2162602207","https://openalex.org/W2168167181","https://openalex.org/W2171150534","https://openalex.org/W2171343266","https://openalex.org/W2171656596","https://openalex.org/W2491497334","https://openalex.org/W2500592175","https://openalex.org/W2950350592","https://openalex.org/W2953100823","https://openalex.org/W4244548826","https://openalex.org/W4308951891","https://openalex.org/W4388311561","https://openalex.org/W6681235718","https://openalex.org/W6684363390"],"related_works":["https://openalex.org/W4293734197","https://openalex.org/W4206967254","https://openalex.org/W2131689821","https://openalex.org/W2097627380","https://openalex.org/W2914864478","https://openalex.org/W2008338582","https://openalex.org/W4291700620","https://openalex.org/W1999586157","https://openalex.org/W22044811","https://openalex.org/W2625329765"],"abstract_inverted_index":{"Clusters":[0],"in":[1,75,100,198],"document":[2],"streams,":[3],"such":[4],"as":[5,16,18,65],"online":[6,147],"news":[7,177],"articles,":[8,178],"can":[9,184],"be":[10],"induced":[11],"by":[12,19],"their":[13,24],"textual":[14],"contents,":[15,149],"well":[17],"the":[20,40,66,83,88,108,116,136,143,152,157,162],"temporal":[21,113,131,190],"dynamics":[22,160],"of":[23,32,39,82,91,110,138,146,161,200,206],"arriving":[25],"patterns.":[26],"Can":[27],"we":[28,57],"leverage":[29],"both":[30,73,172,186],"sources":[31],"information":[33,44,74],"to":[34,49,64,69,93,96,107,141,156,194],"obtain":[35],"a":[36,59,76,123],"better":[37,195],"clustering":[38],"documents,":[41],"and":[42,130,174,179,189,203],"distill":[43],"that":[45,87,181],"is":[46,86,103],"not":[47],"possible":[48],"extract":[50],"using":[51],"contents":[52],"only?":[53],"In":[54],"this":[55],"paper,":[56],"propose":[58],"novel":[60],"random":[61],"process,":[62,68],"referred":[63],"Dirichlet-Hawkes":[67,182],"take":[70],"into":[71],"account":[72],"unified":[77],"framework.":[78],"A":[79],"distinctive":[80],"feature":[81],"proposed":[84],"model":[85,121],"preferential":[89],"attachment":[90],"items":[92],"clusters":[94,139],"according":[95,106],"cluster":[97],"sizes,":[98],"present":[99],"Dirichlet":[101],"processes,":[102,115],"now":[104],"driven":[105],"intensities":[109],"cluster-wise":[111],"self-exciting":[112],"point":[114],"Hawkes":[117],"processes.":[118],"This":[119],"new":[120],"establishes":[122],"previously":[124],"unexplored":[125],"connection":[126],"between":[127],"Bayesian":[128],"Nonparametrics":[129],"Point":[132],"Processes,":[133],"which":[134,192],"makes":[135],"number":[137],"grow":[140],"accommodate":[142],"increasing":[144],"complexity":[145],"streaming":[148],"while":[150],"at":[151],"same":[153],"time":[154,205],"adapts":[155],"ever":[158],"changing":[159],"respective":[163],"continuous":[164],"arrival":[165,204],"time.":[166],"We":[167],"conducted":[168],"large-scale":[169],"experiments":[170],"on":[171],"synthetic":[173],"real":[175],"world":[176],"show":[180],"processes":[183],"recover":[185],"meaningful":[187],"topics":[188],"dynamics,":[191],"leads":[193],"predictive":[196],"performance":[197],"terms":[199],"content":[201],"perplexity":[202],"future":[207],"documents.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":24},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}