{"id":"https://openalex.org/W2783800533","doi":"https://doi.org/10.1109/bigdata.2017.8258394","title":"bigNN: An open-source big data toolkit focused on biomedical sentence classification","display_name":"bigNN: An open-source big data toolkit focused on biomedical sentence classification","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2783800533","doi":"https://doi.org/10.1109/bigdata.2017.8258394","mag":"2783800533"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2017.8258394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8258394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5067918441","display_name":"Ahmad P. Tafti","orcid":"https://orcid.org/0000-0001-9650-2862"},"institutions":[{"id":"https://openalex.org/I1315135799","display_name":"Marshfield Clinic","ror":"https://ror.org/025chrz76","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1315135799"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ahmad P. Tafti","raw_affiliation_strings":["Biomedical Informatics Research Center, Marshfield Clinic Research Institute, WI, USA"],"affiliations":[{"raw_affiliation_string":"Biomedical Informatics Research Center, Marshfield Clinic Research Institute, WI, USA","institution_ids":["https://openalex.org/I1315135799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047873620","display_name":"Ehsun Behravesh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ehsun Behravesh","raw_affiliation_strings":["Kuala Lumpur, Malaysia"],"affiliations":[{"raw_affiliation_string":"Kuala Lumpur, Malaysia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084703739","display_name":"Mehdi Assefi","orcid":null},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehdi Assefi","raw_affiliation_strings":["Department of Computer Science, University of Georgia, GA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Georgia, GA, USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057230789","display_name":"Eric LaRose","orcid":"https://orcid.org/0000-0003-4292-0086"},"institutions":[{"id":"https://openalex.org/I1315135799","display_name":"Marshfield Clinic","ror":"https://ror.org/025chrz76","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1315135799"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric LaRose","raw_affiliation_strings":["Biomedical Informatics Research Center, Marshfield Clinic Research Institute, WI, USA"],"affiliations":[{"raw_affiliation_string":"Biomedical Informatics Research Center, Marshfield Clinic Research Institute, WI, USA","institution_ids":["https://openalex.org/I1315135799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041944660","display_name":"Jonathan Badger","orcid":"https://orcid.org/0000-0001-9924-2648"},"institutions":[{"id":"https://openalex.org/I1315135799","display_name":"Marshfield Clinic","ror":"https://ror.org/025chrz76","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1315135799"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Badger","raw_affiliation_strings":["Biomedical Informatics Research Center, Marshfield Clinic Research Institute, WI, USA"],"affiliations":[{"raw_affiliation_string":"Biomedical Informatics Research Center, Marshfield Clinic Research Institute, WI, USA","institution_ids":["https://openalex.org/I1315135799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053486176","display_name":"John Mayer","orcid":"https://orcid.org/0000-0002-6862-1052"},"institutions":[{"id":"https://openalex.org/I1315135799","display_name":"Marshfield Clinic","ror":"https://ror.org/025chrz76","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1315135799"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Mayer","raw_affiliation_strings":["Biomedical Informatics Research Center, Marshfield Clinic Research Institute, WI, USA"],"affiliations":[{"raw_affiliation_string":"Biomedical Informatics Research Center, Marshfield Clinic Research Institute, WI, USA","institution_ids":["https://openalex.org/I1315135799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110256670","display_name":"AnHai Doan","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"AnHai Doan","raw_affiliation_strings":["Departments of Computer Science, University of Wisconsin-Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"Departments of Computer Science, University of Wisconsin-Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068251706","display_name":"David Page","orcid":"https://orcid.org/0000-0003-0576-2912"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Page","raw_affiliation_strings":["Departments of Computer Science, University of Wisconsin-Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"Departments of Computer Science, University of Wisconsin-Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088183118","display_name":"Peggy Peissig","orcid":"https://orcid.org/0000-0003-4156-0189"},"institutions":[{"id":"https://openalex.org/I1315135799","display_name":"Marshfield Clinic","ror":"https://ror.org/025chrz76","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1315135799"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peggy Peissig","raw_affiliation_strings":["Biomedical Informatics Research Center, Marshfield Clinic Research Institute, WI, USA"],"affiliations":[{"raw_affiliation_string":"Biomedical Informatics Research Center, Marshfield Clinic Research Institute, WI, USA","institution_ids":["https://openalex.org/I1315135799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5067918441"],"corresponding_institution_ids":["https://openalex.org/I1315135799"],"apc_list":null,"apc_paid":null,"fwci":1.1697,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.7856666,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3888","last_page":"3896"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.996999979019165,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.996999979019165,"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/T10028","display_name":"Topic Modeling","score":0.9854000210762024,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.906499981880188,"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/open-source","display_name":"Open source","score":0.8274650573730469},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7606247663497925},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6503722667694092},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.637092113494873},{"id":"https://openalex.org/keywords/open-source-software","display_name":"Open source software","score":0.4345451891422272},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.42839524149894714},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37484389543533325},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36789947748184204},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.33500874042510986},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18445554375648499},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.16815313696861267},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.09649959206581116}],"concepts":[{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.8274650573730469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7606247663497925},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6503722667694092},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.637092113494873},{"id":"https://openalex.org/C2988343187","wikidata":"https://www.wikidata.org/wiki/Q1130645","display_name":"Open source software","level":3,"score":0.4345451891422272},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.42839524149894714},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37484389543533325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36789947748184204},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33500874042510986},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18445554375648499},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.16815313696861267},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.09649959206581116}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2017.8258394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8258394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W295894637","https://openalex.org/W1560851690","https://openalex.org/W1614298861","https://openalex.org/W1951325712","https://openalex.org/W1980748255","https://openalex.org/W2020278455","https://openalex.org/W2057706627","https://openalex.org/W2107141268","https://openalex.org/W2130284530","https://openalex.org/W2131571251","https://openalex.org/W2131744502","https://openalex.org/W2131834529","https://openalex.org/W2134036914","https://openalex.org/W2137349054","https://openalex.org/W2159709123","https://openalex.org/W2170240176","https://openalex.org/W2187898940","https://openalex.org/W2208234687","https://openalex.org/W2212494754","https://openalex.org/W2251874715","https://openalex.org/W2296283641","https://openalex.org/W2620571791","https://openalex.org/W2727053942","https://openalex.org/W2735364069","https://openalex.org/W2772514355","https://openalex.org/W2949952998","https://openalex.org/W2950577311","https://openalex.org/W2952174148","https://openalex.org/W2962715821","https://openalex.org/W2963012544","https://openalex.org/W2963676207","https://openalex.org/W2963682821","https://openalex.org/W6679775712","https://openalex.org/W6685053522","https://openalex.org/W6685189238"],"related_works":["https://openalex.org/W4376877853","https://openalex.org/W1493891899","https://openalex.org/W4250928611","https://openalex.org/W166480398","https://openalex.org/W167327709","https://openalex.org/W1977393088","https://openalex.org/W4387839566","https://openalex.org/W4210922265","https://openalex.org/W2491403535","https://openalex.org/W2108777707"],"abstract_inverted_index":{"Every":[0],"single":[1],"day,":[2],"a":[3,38,101],"massive":[4],"amount":[5],"of":[6,34,81,149],"text":[7,84,95],"data":[8,14,35,56,71,122,129],"is":[9,36,159,164],"generated":[10],"by":[11,139],"different":[12,146],"medical":[13,20],"sources,":[15],"such":[16],"as":[17],"scientific":[18],"literature,":[19],"web":[21],"pages,":[22],"health-related":[23],"social":[24],"media,":[25],"clinical":[26],"notes,":[27],"and":[28,41,48,58,66,93,110,131,144,153,162,166],"drug":[29],"reviews.":[30],"Processing":[31],"this":[32,62],"wealth":[33],"indeed":[37],"daunting":[39],"task,":[40],"it":[42,163],"forces":[43],"us":[44],"to":[45,142],"adopt":[46],"smart":[47],"scalable":[49],"computational":[50],"strategies,":[51],"including":[52],"machine":[53],"intelligence,":[54],"big":[55,70,121,128],"analytics,":[57],"distributed":[59],"architecture.":[60],"In":[61],"contribution,":[63],"we":[64],"designed":[65],"developed":[67],"an":[68,87],"open-source":[69],"neural":[72,103,155],"network":[73,104,156],"toolkit,":[74],"namely":[75],"bigNN":[76,98,158],"which":[77],"tackles":[78],"the":[79,154],"problem":[80],"large-scale":[82],"biomedical":[83],"classification":[85],"in":[86,136],"efficient":[88,120],"fashion,":[89],"facilitating":[90],"fast":[91],"prototyping":[92],"reproducible":[94],"analytics":[96],"researches.":[97],"scales":[99],"up":[100],"word2vec-based":[102],"model":[105],"over":[106],"Apache":[107,151],"Spark":[108,152],"2.10":[109],"Hadoop":[111],"Distributed":[112],"File":[113],"System":[114],"(HDFS)":[115],"2.7.3,":[116],"allowing":[117,140],"for":[118],"more":[119],"sentence":[123,137],"classification.":[124],"The":[125],"toolkit":[126],"supports":[127],"computing,":[130],"simplifies":[132],"rapid":[133],"application":[134],"development":[135],"analysis":[138],"users":[141],"configure":[143],"examine":[145],"internal":[147],"parameters":[148],"both":[150],"model.":[157],"fully":[160],"documented,":[161],"publicly":[165],"freely":[167],"available":[168],"at":[169],"https://github.com/bircatmcri/bigNN.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}