{"id":"https://openalex.org/W2937988243","doi":"https://doi.org/10.1145/3314545.3314566","title":"Using Spark and Scala for Discovering Latent Trends in Job Markets","display_name":"Using Spark and Scala for Discovering Latent Trends in Job Markets","publication_year":2019,"publication_date":"2019-03-14","ids":{"openalex":"https://openalex.org/W2937988243","doi":"https://doi.org/10.1145/3314545.3314566","mag":"2937988243"},"language":"en","primary_location":{"id":"doi:10.1145/3314545.3314566","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3314545.3314566","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 3rd International Conference on Compute and Data Analysis","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/A5085740186","display_name":"Raymond Blanch K. Mbah","orcid":null},"institutions":[{"id":"https://openalex.org/I161515732","display_name":"University of St. Thomas - Minnesota","ror":"https://ror.org/05vfxvp80","country_code":"US","type":"education","lineage":["https://openalex.org/I161515732"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Raymond Blanch K. Mbah","raw_affiliation_strings":["University of St. Thomas, St. Paul, MN, USA"],"affiliations":[{"raw_affiliation_string":"University of St. Thomas, St. Paul, MN, USA","institution_ids":["https://openalex.org/I161515732"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038950029","display_name":"Manjeet Rege","orcid":"https://orcid.org/0009-0003-7643-2598"},"institutions":[{"id":"https://openalex.org/I161515732","display_name":"University of St. Thomas - Minnesota","ror":"https://ror.org/05vfxvp80","country_code":"US","type":"education","lineage":["https://openalex.org/I161515732"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manjeet Rege","raw_affiliation_strings":["University of St. Thomas, St. Paul, MN, USA"],"affiliations":[{"raw_affiliation_string":"University of St. Thomas, St. Paul, MN, USA","institution_ids":["https://openalex.org/I161515732"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032157625","display_name":"Bhabani Misra","orcid":null},"institutions":[{"id":"https://openalex.org/I161515732","display_name":"University of St. Thomas - Minnesota","ror":"https://ror.org/05vfxvp80","country_code":"US","type":"education","lineage":["https://openalex.org/I161515732"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhabani Misra","raw_affiliation_strings":["University of St. Thomas, St Paul, MN, USA"],"affiliations":[{"raw_affiliation_string":"University of St. Thomas, St Paul, MN, USA","institution_ids":["https://openalex.org/I161515732"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085740186"],"corresponding_institution_ids":["https://openalex.org/I161515732"],"apc_list":null,"apc_paid":null,"fwci":0.5942,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71298579,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"55","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9962999820709229,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9941999912261963,"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/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.8119751214981079},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.739528238773346},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7315666079521179},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7277328968048096},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6548932194709778},{"id":"https://openalex.org/keywords/scala","display_name":"Scala","score":0.6065701246261597},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4230739176273346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35452932119369507},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.26235416531562805},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10391765832901001},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.09491604566574097}],"concepts":[{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.8119751214981079},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.739528238773346},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7315666079521179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7277328968048096},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6548932194709778},{"id":"https://openalex.org/C109701466","wikidata":"https://www.wikidata.org/wiki/Q460584","display_name":"Scala","level":3,"score":0.6065701246261597},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4230739176273346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35452932119369507},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26235416531562805},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10391765832901001},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.09491604566574097},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3314545.3314566","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3314545.3314566","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 3rd International Conference on Compute and Data Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1646074461","https://openalex.org/W1880262756","https://openalex.org/W1967082914","https://openalex.org/W1983578042","https://openalex.org/W2004052136","https://openalex.org/W2007863696","https://openalex.org/W2034714661","https://openalex.org/W2049962828","https://openalex.org/W2079153738","https://openalex.org/W2089391273","https://openalex.org/W2091879664","https://openalex.org/W2102160377","https://openalex.org/W2134731454","https://openalex.org/W2436849015","https://openalex.org/W2498778289","https://openalex.org/W2556575288","https://openalex.org/W2912724389","https://openalex.org/W3013669377"],"related_works":["https://openalex.org/W2763674625","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W4252019479","https://openalex.org/W3211874991","https://openalex.org/W2337519567","https://openalex.org/W2548921709","https://openalex.org/W4252076541"],"abstract_inverted_index":{"Job":[0],"markets":[1,115],"are":[2],"experiencing":[3],"an":[4],"exponential":[5],"growth":[6],"in":[7,16,84,98,113,158],"data":[8,15,118],"alongside":[9],"the":[10],"recent":[11],"explosion":[12],"of":[13,37,109],"big":[14,117],"various":[17],"domains":[18],"including":[19],"health,":[20],"security":[21],"and":[22,33,87,96,122,124],"finance.":[23],"Staying":[24],"current":[25],"with":[26,42,51],"job":[27,44,59,85,99,114],"market":[28],"trends":[29,97,112],"entails":[30],"collecting,":[31],"processing":[32],"analyzing":[34,43],"huge":[35],"amounts":[36],"data.":[38],"A":[39],"typical":[40],"challenge":[41],"listings":[45,86],"is":[46],"that":[47,141,152],"they":[48],"vary":[49],"drastically":[50],"regards":[52],"to":[53,66,79],"verbiage,":[54],"for":[55],"instance":[56],"a":[57,74,106],"given":[58],"title":[60],"or":[61,70],"skill":[62],"can":[63,138],"be":[64],"referred":[65],"using":[67,116,147],"different":[68],"words":[69,82],"industry":[71],"jargons.":[72],"As":[73],"result,":[75],"it":[76],"becomes":[77],"incumbent":[78],"go":[80],"beyond":[81],"present":[83,105],"carry":[88],"out":[89],"analysis":[90,132],"aimed":[91],"at":[92],"discovering":[93],"latent":[94,111,130],"structures":[95],"listings.":[100],"In":[101],"this":[102],"paper,":[103],"we":[104],"systematic":[107],"approach":[108],"uncovering":[110],"technologies":[119],"(Apache":[120],"Spark":[121],"Scala)":[123],"distributed":[125],"semantic":[126,131],"techniques":[127,151],"such":[128],"as":[129],"(LSA).":[133],"We":[134],"show":[135],"how":[136],"LSA":[137],"uncover":[139],"patterns/relationships/trends":[140],"will":[142],"otherwise":[143],"remain":[144],"hidden":[145],"if":[146],"traditional":[148],"text":[149],"mining":[150],"rely":[153],"only":[154],"on":[155],"word":[156],"frequencies":[157],"documents.":[159]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}