{"id":"https://openalex.org/W2068834169","doi":"https://doi.org/10.1109/bigdata.2014.7004356","title":"WS<sup>2</sup>F: A weakly supervised framework for data stream filtering","display_name":"WS<sup>2</sup>F: A weakly supervised framework for data stream filtering","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2068834169","doi":"https://doi.org/10.1109/bigdata.2014.7004356","mag":"2068834169"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2014.7004356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","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/A5000605124","display_name":"Cailing Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I126744593","display_name":"University of Maryland, Baltimore","ror":"https://ror.org/04rq5mt64","country_code":"US","type":"education","lineage":["https://openalex.org/I126744593"]},{"id":"https://openalex.org/I173498003","display_name":"Palo Alto Research Center","ror":"https://ror.org/0529fxt39","country_code":"US","type":"facility","lineage":["https://openalex.org/I173498003","https://openalex.org/I4210132870"]},{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cailing Dong","raw_affiliation_strings":["Department of Information Systems University of Maryland, Baltimore, MD","Palo Alto Research Center, Webster, NY","Department of Information Systems, University of Maryland, Baltimore County, Baltimore, MD 21250"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems University of Maryland, Baltimore, MD","institution_ids":["https://openalex.org/I126744593"]},{"raw_affiliation_string":"Palo Alto Research Center, Webster, NY","institution_ids":["https://openalex.org/I173498003"]},{"raw_affiliation_string":"Department of Information Systems, University of Maryland, Baltimore County, Baltimore, MD 21250","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023738988","display_name":"Arvind Agarwal","orcid":"https://orcid.org/0000-0002-7052-653X"},"institutions":[{"id":"https://openalex.org/I173498003","display_name":"Palo Alto Research Center","ror":"https://ror.org/0529fxt39","country_code":"US","type":"facility","lineage":["https://openalex.org/I173498003","https://openalex.org/I4210132870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arvind Agarwal","raw_affiliation_strings":["Palo Alto Research Center, Webster, New York","Palo Alto Research Center, 800 Phillips Rd, Bldg 128, Webster, NY, 14580"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Palo Alto Research Center, Webster, New York","institution_ids":["https://openalex.org/I173498003"]},{"raw_affiliation_string":"Palo Alto Research Center, 800 Phillips Rd, Bldg 128, Webster, NY, 14580","institution_ids":["https://openalex.org/I173498003"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4229,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.75324138,"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":"50","last_page":"57"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","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"}},"topics":[{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9976999759674072,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9968000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.7723814845085144},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7678591012954712},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7439913153648376},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.7010593414306641},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6340624094009399},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.613827645778656},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5090048313140869},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.4908212125301361},{"id":"https://openalex.org/keywords/line","display_name":"Line (geometry)","score":0.4484015107154846},{"id":"https://openalex.org/keywords/fraction","display_name":"Fraction (chemistry)","score":0.4243292808532715},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.42016157507896423},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.38800349831581116},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2483433187007904},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08169257640838623}],"concepts":[{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.7723814845085144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7678591012954712},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7439913153648376},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.7010593414306641},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6340624094009399},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.613827645778656},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5090048313140869},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.4908212125301361},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.4484015107154846},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.4243292808532715},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.42016157507896423},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.38800349831581116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2483433187007904},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08169257640838623},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2014.7004356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W59992493","https://openalex.org/W1531719573","https://openalex.org/W1743243001","https://openalex.org/W1901600440","https://openalex.org/W1973897992","https://openalex.org/W1983012012","https://openalex.org/W1998224037","https://openalex.org/W1998257453","https://openalex.org/W2045442501","https://openalex.org/W2069557380","https://openalex.org/W2089085556","https://openalex.org/W2123661878","https://openalex.org/W2124499489","https://openalex.org/W2133845513","https://openalex.org/W2137553870","https://openalex.org/W2140427797","https://openalex.org/W2145139979","https://openalex.org/W2157765050","https://openalex.org/W2159681823","https://openalex.org/W2165550819","https://openalex.org/W2166353350","https://openalex.org/W2168332560","https://openalex.org/W2339562433","https://openalex.org/W2399079233","https://openalex.org/W3005822403","https://openalex.org/W4233787372","https://openalex.org/W6602463920","https://openalex.org/W6637805623","https://openalex.org/W6680455949","https://openalex.org/W6681477759","https://openalex.org/W6683147150","https://openalex.org/W6684347184","https://openalex.org/W6703967046"],"related_works":["https://openalex.org/W1191014223","https://openalex.org/W178140751","https://openalex.org/W1137063513","https://openalex.org/W4250539519","https://openalex.org/W4387682966","https://openalex.org/W3093605827","https://openalex.org/W1521014365","https://openalex.org/W2207622907","https://openalex.org/W2366031425","https://openalex.org/W2080431242"],"abstract_inverted_index":{"In":[0,77],"this":[1,78],"paper":[2],"we":[3,80],"present":[4,81],"a":[5,24,40,82,168,208],"weakly":[6],"supervised":[7],"framework":[8,83,106,145,217],"for":[9,138,223],"relevant":[10,89,166,191,221],"content":[11,165,222],"filtering":[12],"from":[13,91],"social":[14,102,153],"media":[15,21,103,154],"platforms":[16,22,155],"such":[17],"as":[18,171,201],"Twitter.":[19],"Social":[20],"are":[23,66],"rich":[25],"source":[26],"of":[27,32,43,46,50,74,98,118,125,152,179],"information":[28,53,90,94],"these":[29],"days.":[30],"However":[31],"all":[33],"the":[34,51,63,87,92,96,123,149,164,175,190,202,216],"available":[35],"information,":[36],"there":[37],"is":[38,45,59,70,116,134,146,160,184],"only":[39,186,219],"small":[41],"fraction":[42],"which":[44],"general":[47,75],"interest.":[48,76],"Most":[49],"other":[52],"pertains":[54],"to":[55,62,84,162,167,188,196],"personal":[56],"events,":[57],"and":[58,127,141,213],"very":[60],"specific":[61,169],"users":[64],"who":[65],"contributing":[67],"that.":[68],"It":[69,133],"therefore":[71,135],"usually":[72],"not":[73,108,185,218],"paper,":[79],"filter":[85,189],"out":[86],"topic-specific":[88],"irrelevant":[93],"in":[95,122,156,174],"stream":[97],"text":[99,176],"provided":[100,129,210],"by":[101,130,211],"platforms.":[104],"Our":[105],"does":[107],"depend":[109],"on":[110,207],"any":[111],"labeled":[112],"data,":[113],"however":[114],"it":[115,159,172,183],"capable":[117],"using":[119],"domain":[120,131],"knowledge":[121],"form":[124],"rules":[126],"guidelines":[128],"experts.":[132],"easily":[136],"extensible":[137],"new":[139],"topics":[140],"events.":[142],"The":[143],"proposed":[144],"built":[147],"keeping":[148],"streaming":[150],"nature":[151],"mind,":[157],"i.e.,":[158],"able":[161,187,195],"discover":[163],"event":[170,198,203,225],"evolves":[173],"stream.":[177],"Because":[178],"its":[180,229],"adaptive":[181],"nature,":[182],"content,":[192],"but":[193,226],"also":[194,227],"generate":[197],"story":[199,230],"lines":[200],"evolves.":[204],"We":[205],"experiment":[206],"dataset":[209],"TREC,":[212],"show":[214],"that":[215],"filters":[220],"an":[224],"generates":[228],"line":[231],"effectively.":[232]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}