{"id":"https://openalex.org/W2004192095","doi":"https://doi.org/10.1145/2484028.2484166","title":"Improving LDA topic models for microblogs via tweet pooling and automatic labeling","display_name":"Improving LDA topic models for microblogs via tweet pooling and automatic labeling","publication_year":2013,"publication_date":"2013-07-28","ids":{"openalex":"https://openalex.org/W2004192095","doi":"https://doi.org/10.1145/2484028.2484166","mag":"2004192095"},"language":"en","primary_location":{"id":"doi:10.1145/2484028.2484166","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2484028.2484166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th 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/A5018503243","display_name":"Rishabh Mehrotra","orcid":"https://orcid.org/0000-0002-0836-4605"},"institutions":[{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Rishabh Mehrotra","raw_affiliation_strings":["BITS Pilani, Pilani, India"],"affiliations":[{"raw_affiliation_string":"BITS Pilani, Pilani, India","institution_ids":["https://openalex.org/I74796645"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028174137","display_name":"Scott Sanner","orcid":"https://orcid.org/0000-0001-7984-8394"},"institutions":[{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Scott Sanner","raw_affiliation_strings":["NICTA & ANU, Canberra, Australia","NICTA & ANU, Canberra, Australia#TAB#"],"affiliations":[{"raw_affiliation_string":"NICTA & ANU, Canberra, Australia","institution_ids":["https://openalex.org/I42894916"]},{"raw_affiliation_string":"NICTA & ANU, Canberra, Australia#TAB#","institution_ids":["https://openalex.org/I42894916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005792924","display_name":"Wray Buntine","orcid":"https://orcid.org/0000-0001-9292-1015"},"institutions":[{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wray Buntine","raw_affiliation_strings":["NICTA & ANU, Canberra, Australia","NICTA & ANU, Canberra, Australia#TAB#"],"affiliations":[{"raw_affiliation_string":"NICTA & ANU, Canberra, Australia","institution_ids":["https://openalex.org/I42894916"]},{"raw_affiliation_string":"NICTA & ANU, Canberra, Australia#TAB#","institution_ids":["https://openalex.org/I42894916"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049449495","display_name":"Lexing Xie","orcid":"https://orcid.org/0000-0001-8319-0118"},"institutions":[{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lexing Xie","raw_affiliation_strings":["ANU & NICTA, Canberra, Australia","ANU and NICTA, Canberra, Australia#TAB#"],"affiliations":[{"raw_affiliation_string":"ANU & NICTA, Canberra, Australia","institution_ids":["https://openalex.org/I42894916"]},{"raw_affiliation_string":"ANU and NICTA, Canberra, Australia#TAB#","institution_ids":["https://openalex.org/I42894916"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5018503243"],"corresponding_institution_ids":["https://openalex.org/I74796645"],"apc_list":null,"apc_paid":null,"fwci":24.6747,"has_fulltext":false,"cited_by_count":473,"citation_normalized_percentile":{"value":0.99771551,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"889","last_page":"892"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9976999759674072,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.991599977016449,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.9245834350585938},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.9077998399734497},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7713437676429749},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.7699381709098816},{"id":"https://openalex.org/keywords/microblogging","display_name":"Microblogging","score":0.7249545454978943},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.670830249786377},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.598170280456543},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5829826593399048},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4981503486633301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44662150740623474},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42242157459259033},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.4140816330909729},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37392961978912354},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32635611295700073},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3235061764717102},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.23115476965904236}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.9245834350585938},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.9077998399734497},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7713437676429749},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.7699381709098816},{"id":"https://openalex.org/C143275388","wikidata":"https://www.wikidata.org/wiki/Q92438","display_name":"Microblogging","level":3,"score":0.7249545454978943},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.670830249786377},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.598170280456543},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5829826593399048},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4981503486633301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44662150740623474},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42242157459259033},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.4140816330909729},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37392961978912354},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32635611295700073},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3235061764717102},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.23115476965904236},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2484028.2484166","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2484028.2484166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.649.6734","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.649.6734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://users.cecs.anu.edu.au/~ssanner/Papers/sigir13.pdf","raw_type":"text"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/65728","is_oa":false,"landing_page_url":"http://hdl.handle.net/1885/65728","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W157541337","https://openalex.org/W1532325895","https://openalex.org/W1880262756","https://openalex.org/W1956559956","https://openalex.org/W1974548136","https://openalex.org/W2016443085","https://openalex.org/W2056076776","https://openalex.org/W2063904635","https://openalex.org/W2076219102","https://openalex.org/W2104894372","https://openalex.org/W2137958601","https://openalex.org/W2147946282","https://openalex.org/W2168332560","https://openalex.org/W2171319841","https://openalex.org/W2325227998","https://openalex.org/W6640862754","https://openalex.org/W6680441624","https://openalex.org/W6682044806"],"related_works":["https://openalex.org/W1463179486","https://openalex.org/W2769501189","https://openalex.org/W4315588616","https://openalex.org/W4312773271","https://openalex.org/W2888805565","https://openalex.org/W2494246486","https://openalex.org/W2207653751","https://openalex.org/W2339938268","https://openalex.org/W2611137333","https://openalex.org/W2122605835"],"abstract_inverted_index":{"Twitter,":[0],"or":[1],"the":[2,11,69,144],"world":[3],"of":[4,13,33,72,98,111,131,137,151],"140":[5],"characters":[6],"poses":[7],"serious":[8],"challenges":[9],"to":[10,36,49,60,104,123,159],"efficacy":[12],"topic":[14,21,114,163],"models":[15,22,164],"on":[16,143,165],"short,":[17],"messy":[18],"text.":[19],"While":[20],"such":[23],"as":[24],"Latent":[25],"Dirichlet":[26],"Allocation":[27],"(LDA)":[28],"have":[29],"a":[30,85,95,105,109,129,149],"long":[31],"history":[32],"successful":[34],"application":[35],"news":[37],"articles":[38],"and":[39,128],"academic":[40],"abstracts,":[41],"they":[42],"are":[43],"often":[44],"less":[45],"coherent":[46],"when":[47],"applied":[48],"microblog":[50],"content":[51,66],"like":[52],"Twitter.":[53],"In":[54],"this":[55,76],"paper,":[56],"we":[57,74],"investigate":[58],"methods":[59],"improve":[61],"topics":[62],"learned":[63],"from":[64],"Twitter":[65,119,166],"without":[67],"modifying":[68],"basic":[70],"machinery":[71],"LDA;":[73],"achieve":[75],"through":[77],"various":[78],"pooling":[79,100,132,146],"schemes":[80,157],"that":[81,94],"aggregate":[82],"tweets":[83],"in":[84,108,121],"data":[86],"preprocessing":[87],"step":[88],"for":[89,113,148],"LDA.":[90],"We":[91],"empirically":[92],"establish":[93],"novel":[96,156],"method":[97],"tweet":[99],"by":[101],"hashtags":[102],"leads":[103],"vast":[106],"improvement":[107],"variety":[110,130],"measures":[112],"coherence":[115],"across":[116],"three":[117],"diverse":[118],"datasets":[120],"comparison":[122],"an":[124],"unmodified":[125],"LDA":[126,162],"baseline":[127],"schemes.":[133],"An":[134],"additional":[135],"contribution":[136],"automatic":[138],"hashtag":[139,145],"labeling":[140],"further":[141],"improves":[142],"results":[147],"subset":[150],"metrics.":[152],"Overall,":[153],"these":[154],"two":[155],"lead":[158],"significantly":[160],"improved":[161],"content.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":47},{"year":2021,"cited_by_count":56},{"year":2020,"cited_by_count":59},{"year":2019,"cited_by_count":51},{"year":2018,"cited_by_count":57},{"year":2017,"cited_by_count":50},{"year":2016,"cited_by_count":46},{"year":2015,"cited_by_count":29},{"year":2014,"cited_by_count":23},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}