{"id":"https://openalex.org/W2007579527","doi":"https://doi.org/10.1145/2513577.2513582","title":"Scalable mining of social data using stochastic gradient fisher scoring","display_name":"Scalable mining of social data using stochastic gradient fisher scoring","publication_year":2013,"publication_date":"2013-10-28","ids":{"openalex":"https://openalex.org/W2007579527","doi":"https://doi.org/10.1145/2513577.2513582","mag":"2007579527"},"language":"en","primary_location":{"id":"doi:10.1145/2513577.2513582","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2513577.2513582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 workshop on Data-driven user behavioral modelling and mining from social media","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/A5028163163","display_name":"Jeon-Hyung Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jeon-Hyung Kang","raw_affiliation_strings":["University of Southern California Information Sciences Institute, Marina del Rey, CA, USA","[University of Southern California, Information Sciences Institute, Marina del Rey, CA, USA]"],"affiliations":[{"raw_affiliation_string":"University of Southern California Information Sciences Institute, Marina del Rey, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"[University of Southern California, Information Sciences Institute, Marina del Rey, CA, USA]","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049634383","display_name":"Kristina Lerman","orcid":"https://orcid.org/0000-0002-5071-0575"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristina Lerman","raw_affiliation_strings":["University of Southern California Information Sciences Institute, Marina del Rey, CA, USA","[University of Southern California, Information Sciences Institute, Marina del Rey, CA, USA]"],"affiliations":[{"raw_affiliation_string":"University of Southern California Information Sciences Institute, Marina del Rey, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"[University of Southern California, Information Sciences Institute, Marina del Rey, CA, USA]","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028163163"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.4942,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.75731166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9988999962806702,"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":0.9988999962806702,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.995199978351593,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9854000210762024,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.774044394493103},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7696437835693359},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.695643424987793},{"id":"https://openalex.org/keywords/microblogging","display_name":"Microblogging","score":0.6589922904968262},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.6159439086914062},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5587443709373474},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.5275356769561768},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5266637206077576},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5027413368225098},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4830813705921173},{"id":"https://openalex.org/keywords/transaction-data","display_name":"Transaction data","score":0.45796114206314087},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4427943825721741},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4286329746246338},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.42577263712882996},{"id":"https://openalex.org/keywords/database-transaction","display_name":"Database transaction","score":0.1469254195690155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.774044394493103},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7696437835693359},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.695643424987793},{"id":"https://openalex.org/C143275388","wikidata":"https://www.wikidata.org/wiki/Q92438","display_name":"Microblogging","level":3,"score":0.6589922904968262},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.6159439086914062},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5587443709373474},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.5275356769561768},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5266637206077576},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5027413368225098},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4830813705921173},{"id":"https://openalex.org/C127722929","wikidata":"https://www.wikidata.org/wiki/Q7833714","display_name":"Transaction data","level":3,"score":0.45796114206314087},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4427943825721741},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4286329746246338},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.42577263712882996},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.1469254195690155},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2513577.2513582","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2513577.2513582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 workshop on Data-driven user behavioral modelling and mining from social media","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.642.4737","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.642.4737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.isi.edu/integration/people/lerman/papers/dubmod05-kang.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1586466971","https://openalex.org/W1682176785","https://openalex.org/W1752870744","https://openalex.org/W1880189740","https://openalex.org/W1880262756","https://openalex.org/W1936677086","https://openalex.org/W1980147176","https://openalex.org/W2114643899","https://openalex.org/W2135790056","https://openalex.org/W2161340280","https://openalex.org/W2166706236","https://openalex.org/W2167433878","https://openalex.org/W2171278750","https://openalex.org/W2949976336","https://openalex.org/W2950770596","https://openalex.org/W2962727278","https://openalex.org/W2962860893","https://openalex.org/W2962961425","https://openalex.org/W6639619044","https://openalex.org/W6684249991"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483","https://openalex.org/W4221142204"],"abstract_inverted_index":{"The":[0],"rapid":[1],"growth":[2],"of":[3,9,57,64,96,103,120,182],"social":[4,18,37,123,160,183],"data":[5,97,124,161,184,199],"in":[6,99,135,141,198],"the":[7,104,110,118,142],"form":[8],"videos,":[10],"microblog":[11],"posts":[12],"and":[13,27,43,48,175],"other":[14,132],"items":[15,197],"shared":[16],"on":[17,179],"media":[19],"presents":[20],"new":[21,55],"opportunities":[22],"for":[23,35,83,122,151],"learning":[24],"user":[25],"behavior":[26],"preferences.":[28],"Bayesian":[29,91],"models":[30],"have":[31,60,202],"been":[32],"used":[33,61],"widely":[34],"modeling":[36],"data,":[38,106,137],"since":[39],"they":[40],"capture":[41],"uncertainty":[42],"prior":[44],"knowledge,":[45],"avoid":[46],"overfitting,":[47],"can":[49],"be":[50],"easily":[51],"extended":[52],"to":[53,67,107,153,193],"incorporate":[54],"types":[56],"data.":[58,72],"Researchers":[59],"a":[62,90,180,203],"variety":[63,181],"inference":[65,111,133],"procedures":[66],"learn":[68,154],"model":[69],"parameters":[70],"from":[71,89],"Specifically,":[73],"Stochastic":[74],"Gradient":[75],"Fisher":[76],"Scoring":[77],"(SGFS)":[78],"method":[79,87],"was":[80],"recently":[81],"proposed":[82],"efficient":[84],"inference.":[85],"This":[86,156],"samples":[88,98],"posterior":[92],"using":[93],"small":[94],"number":[95],"each":[100],"iteration,":[101],"instead":[102],"entire":[105],"speed":[108],"up":[109],"process.":[112],"In":[113],"this":[114,168],"paper":[115],"we":[116,170],"explore":[117],"feasibility":[119],"SGFS":[121,129,173],"mining.":[125],"We":[126,186],"find":[127,187],"that":[128,188,201],"often":[130,162],"outperforms":[131],"methods":[134],"dense":[136],"but":[138],"it":[139,152],"fails":[140],"sparse":[143],"\"long-tail\"":[144],"where":[145],"there":[146],"are":[147],"not":[148],"enough":[149],"instances":[150],"parameters.":[155],"is":[157,190],"problematic,":[158],"because":[159],"has":[163],"long-tailed":[164,204],"distribution.":[165,205],"To":[166],"address":[167],"problem,":[169],"propose":[171],"hybrid":[172],"(hSGFS)":[174],"evaluate":[176],"its":[177],"performance":[178],"sets.":[185],"hSGFS":[189],"better":[191],"able":[192],"predict":[194],"held":[195],"out":[196],"sets":[200]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}