{"id":"https://openalex.org/W4214895456","doi":"https://doi.org/10.1109/ccwc54503.2022.9720765","title":"Efficient Large Scale NLP Feature Engineering with Apache Spark","display_name":"Efficient Large Scale NLP Feature Engineering with Apache Spark","publication_year":2022,"publication_date":"2022-01-26","ids":{"openalex":"https://openalex.org/W4214895456","doi":"https://doi.org/10.1109/ccwc54503.2022.9720765"},"language":"en","primary_location":{"id":"doi:10.1109/ccwc54503.2022.9720765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccwc54503.2022.9720765","pdf_url":null,"source":{"id":"https://openalex.org/S4363608098","display_name":"2022 IEEE 12th Annual Computing and Communication Workshop and Conference (CCWC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 12th Annual Computing and Communication Workshop and Conference (CCWC)","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/A5082814342","display_name":"Armin Esmaeilzadeh","orcid":"https://orcid.org/0000-0001-8562-395X"},"institutions":[{"id":"https://openalex.org/I133999245","display_name":"University of Nevada, Las Vegas","ror":"https://ror.org/0406gha72","country_code":"US","type":"education","lineage":["https://openalex.org/I133999245"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Armin Esmaeilzadeh","raw_affiliation_strings":["University of Nevada Las Vegas,Las Vegas,Nevada,USA","University of Nevada Las Vegas, Las Vegas, Nevada, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Nevada Las Vegas,Las Vegas,Nevada,USA","institution_ids":["https://openalex.org/I133999245"]},{"raw_affiliation_string":"University of Nevada Las Vegas, Las Vegas, Nevada, USA","institution_ids":["https://openalex.org/I133999245"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109575594","display_name":"Maryam Heidari","orcid":null},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maryam Heidari","raw_affiliation_strings":["George Mason University,Virginia,USA","George Mason University, Virginia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Mason University,Virginia,USA","institution_ids":["https://openalex.org/I162714631"]},{"raw_affiliation_string":"George Mason University, Virginia, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044657266","display_name":"Reyhaneh Abdolazimi","orcid":"https://orcid.org/0009-0004-7330-0589"},"institutions":[{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reyhaneh Abdolazimi","raw_affiliation_strings":["Syracuse University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Syracuse University","institution_ids":["https://openalex.org/I70983195"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050969529","display_name":"Parisa Hajibabaee","orcid":"https://orcid.org/0000-0003-4449-9774"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Parisa Hajibabaee","raw_affiliation_strings":["University of Massachusetts at Lowell,Lowell,USA","University of Massachusetts at Lowell, Lowell, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts at Lowell,Lowell,USA","institution_ids":["https://openalex.org/I133738476"]},{"raw_affiliation_string":"University of Massachusetts at Lowell, Lowell, USA","institution_ids":["https://openalex.org/I133738476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032130532","display_name":"Masoud Malekzadeh","orcid":"https://orcid.org/0000-0002-0102-2442"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Masoud Malekzadeh","raw_affiliation_strings":["University of Massachusetts at Lowell,Lowell,USA","University of Massachusetts at Lowell, Lowell, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts at Lowell,Lowell,USA","institution_ids":["https://openalex.org/I133738476"]},{"raw_affiliation_string":"University of Massachusetts at Lowell, Lowell, USA","institution_ids":["https://openalex.org/I133738476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6387,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.94266514,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"0274","last_page":"0280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.8607938885688782},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8169428110122681},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7291260957717896},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.7024763822555542},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6685270071029663},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6535876393318176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5997980833053589},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.5304134488105774},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5070979595184326},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4342445731163025},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.433765709400177},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3663417398929596},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32651424407958984},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2528114914894104},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2424633800983429},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23701757192611694},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19570526480674744}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8607938885688782},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8169428110122681},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7291260957717896},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.7024763822555542},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6685270071029663},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6535876393318176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5997980833053589},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.5304134488105774},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5070979595184326},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4342445731163025},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.433765709400177},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3663417398929596},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32651424407958984},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2528114914894104},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2424633800983429},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23701757192611694},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19570526480674744},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/ccwc54503.2022.9720765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccwc54503.2022.9720765","pdf_url":null,"source":{"id":"https://openalex.org/S4363608098","display_name":"2022 IEEE 12th Annual Computing and Communication Workshop and Conference (CCWC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 12th Annual Computing and Communication Workshop and Conference (CCWC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6499355239","display_name":null,"funder_award_id":"1625677","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1522930027","https://openalex.org/W2038412523","https://openalex.org/W2061271742","https://openalex.org/W2098162425","https://openalex.org/W2119738171","https://openalex.org/W2131975293","https://openalex.org/W2173213060","https://openalex.org/W2484828460","https://openalex.org/W2542459869","https://openalex.org/W2567147177","https://openalex.org/W2625392185","https://openalex.org/W2795962243","https://openalex.org/W2803897010","https://openalex.org/W2885170888","https://openalex.org/W2888421737","https://openalex.org/W2904275621","https://openalex.org/W2963749793","https://openalex.org/W3041536282","https://openalex.org/W3070452058","https://openalex.org/W3104569204","https://openalex.org/W3112012536","https://openalex.org/W3116492894","https://openalex.org/W3126694655","https://openalex.org/W3132668218","https://openalex.org/W3161346788","https://openalex.org/W3161628534","https://openalex.org/W3163267637","https://openalex.org/W3163910943","https://openalex.org/W3164374254","https://openalex.org/W3168767106","https://openalex.org/W3170977445","https://openalex.org/W3174558664","https://openalex.org/W3176130152","https://openalex.org/W3176267567","https://openalex.org/W3196027777","https://openalex.org/W3201615129","https://openalex.org/W3201707482","https://openalex.org/W3207908651","https://openalex.org/W4200053119","https://openalex.org/W4200604551","https://openalex.org/W4205659634","https://openalex.org/W4206676020","https://openalex.org/W4214824945","https://openalex.org/W4214835615","https://openalex.org/W4214889253","https://openalex.org/W4214937997","https://openalex.org/W4226086088","https://openalex.org/W4295036102","https://openalex.org/W6631307659","https://openalex.org/W6665546858","https://openalex.org/W6679815717","https://openalex.org/W6750639851","https://openalex.org/W6789916643","https://openalex.org/W6790570576","https://openalex.org/W6795330162","https://openalex.org/W6795425767","https://openalex.org/W6795464211","https://openalex.org/W6800243174","https://openalex.org/W6802203764","https://openalex.org/W6803518396","https://openalex.org/W6805372140","https://openalex.org/W6843155303"],"related_works":["https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W2558523485","https://openalex.org/W2799508461","https://openalex.org/W4379407450","https://openalex.org/W2408437972","https://openalex.org/W2905107896"],"abstract_inverted_index":{"Feature":[0],"engineering":[1],"is":[2],"a":[3,75],"computationally":[4],"time-consuming":[5],"process":[6],"in":[7],"the":[8,28,50,53,56,60,69,79,84],"end-to-end":[9],"machine":[10],"learning":[11],"pipeline.":[12],"Large":[13],"amounts":[14],"of":[15,52,59,71,83],"text":[16,66],"data":[17],"are":[18,42],"being":[19],"generated":[20],"on":[21,27],"many":[22],"heterogeneous":[23],"sources":[24],"and":[25,55],"platforms":[26],"internet.":[29],"The":[30],"compute":[31],"resources":[32],"needed":[33],"to":[34,64,87],"extract":[35,65],"valuable":[36],"features":[37,67],"from":[38,68],"these":[39],"big":[40],"datasets":[41],"increasing":[43],"significantly.":[44],"In":[45],"this":[46],"research,":[47],"we":[48,77],"evaluate":[49],"runtime":[51,81],"RDD":[54,88],"Spark-SQL":[57],"APIs":[58],"Apache":[61],"Spark":[62],"framework":[63],"corpus":[70],"english":[72],"Wikipedia.":[73],"As":[74],"result,":[76],"demonstrate":[78],"significant":[80],"performance":[82],"SparkSQL":[85],"compared":[86],"API.":[89]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":11}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}