{"id":"https://openalex.org/W4226040189","doi":"https://doi.org/10.1145/3508072.3508196","title":"A Big Data framework based on Apache Spark for Industry-specific Lexicon Generation for Stock Market Prediction","display_name":"A Big Data framework based on Apache Spark for Industry-specific Lexicon Generation for Stock Market Prediction","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W4226040189","doi":"https://doi.org/10.1145/3508072.3508196"},"language":"en","primary_location":{"id":"doi:10.1145/3508072.3508196","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3508072.3508196","pdf_url":null,"source":{"id":"https://openalex.org/S4363608372","display_name":"The 5th International Conference on Future Networks & Distributed Systems","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":"The 5th International Conference on Future Networks & Distributed Systems","raw_type":"proceedings-article"},"type":"conference-paper","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/A5086636133","display_name":"Simone Angioni","orcid":"https://orcid.org/0000-0002-6682-3419"},"institutions":[{"id":"https://openalex.org/I172446870","display_name":"University of Cagliari","ror":"https://ror.org/003109y17","country_code":"IT","type":"education","lineage":["https://openalex.org/I172446870"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Simone Angioni","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Cagliari, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Cagliari, Italy","institution_ids":["https://openalex.org/I172446870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069275031","display_name":"Salvatore Carta","orcid":"https://orcid.org/0000-0001-9481-511X"},"institutions":[{"id":"https://openalex.org/I172446870","display_name":"University of Cagliari","ror":"https://ror.org/003109y17","country_code":"IT","type":"education","lineage":["https://openalex.org/I172446870"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Salvatore Carta","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Cagliari, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Cagliari, Italy","institution_ids":["https://openalex.org/I172446870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029063875","display_name":"Sergio Consoli","orcid":"https://orcid.org/0000-0001-7357-5858"},"institutions":[{"id":"https://openalex.org/I4210118689","display_name":"Joint Research Centre","ror":"https://ror.org/02qezmz13","country_code":"IT","type":"government","lineage":["https://openalex.org/I1320481043","https://openalex.org/I2800387288","https://openalex.org/I4210118689","https://openalex.org/I4210161702"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sergio Consoli","raw_affiliation_strings":["European Commission, Joint Research Centre (JRC), Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Commission, Joint Research Centre (JRC), Italy","institution_ids":["https://openalex.org/I4210118689"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014673075","display_name":"Diego Reforgiato Recupero","orcid":"https://orcid.org/0000-0001-8646-6183"},"institutions":[{"id":"https://openalex.org/I172446870","display_name":"University of Cagliari","ror":"https://ror.org/003109y17","country_code":"IT","type":"education","lineage":["https://openalex.org/I172446870"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Diego Reforgiato Recupero","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Cagliari, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Cagliari, Italy","institution_ids":["https://openalex.org/I172446870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054679736","display_name":"Maria Madalina Stanciu","orcid":"https://orcid.org/0000-0002-6522-908X"},"institutions":[{"id":"https://openalex.org/I172446870","display_name":"University of Cagliari","ror":"https://ror.org/003109y17","country_code":"IT","type":"education","lineage":["https://openalex.org/I172446870"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Maria Madalina Stanciu","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Cagliari, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Cagliari, Italy","institution_ids":["https://openalex.org/I172446870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":null,"first_page":"616","last_page":"624"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9994000196456909,"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.9994000196456909,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11270","display_name":"Complex Systems and Time Series Analysis","score":0.9775000214576721,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/citation","display_name":"Citation","score":0.5359511971473694},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5166376233100891},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4726502001285553},{"id":"https://openalex.org/keywords/european-commission","display_name":"European commission","score":0.4206288754940033},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3806602656841278},{"id":"https://openalex.org/keywords/library-science","display_name":"Library science","score":0.36990106105804443},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.32908737659454346},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.26847779750823975},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.13272446393966675},{"id":"https://openalex.org/keywords/european-union","display_name":"European union","score":0.09980538487434387}],"concepts":[{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.5359511971473694},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5166376233100891},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4726502001285553},{"id":"https://openalex.org/C3020782553","wikidata":"https://www.wikidata.org/wiki/Q8880","display_name":"European commission","level":3,"score":0.4206288754940033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3806602656841278},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.36990106105804443},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.32908737659454346},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26847779750823975},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.13272446393966675},{"id":"https://openalex.org/C2910001868","wikidata":"https://www.wikidata.org/wiki/Q458","display_name":"European union","level":2,"score":0.09980538487434387},{"id":"https://openalex.org/C105639569","wikidata":"https://www.wikidata.org/wiki/Q582577","display_name":"Economic policy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3508072.3508196","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3508072.3508196","pdf_url":null,"source":{"id":"https://openalex.org/S4363608372","display_name":"The 5th International Conference on Future Networks & Distributed Systems","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":"The 5th International Conference on Future Networks & Distributed Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unica.it:11584/334853","is_oa":false,"landing_page_url":"https://hdl.handle.net/11584/334853","pdf_url":null,"source":{"id":"https://openalex.org/S4377196293","display_name":"UNICA IRIS Institutional Research Information System (University of Cagliari)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172446870","host_organization_name":"University of Cagliari","host_organization_lineage":["https://openalex.org/I172446870"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1094348930","https://openalex.org/W1964590675","https://openalex.org/W2064270391","https://openalex.org/W2094665138","https://openalex.org/W2131773668","https://openalex.org/W2149718612","https://openalex.org/W2164896167","https://openalex.org/W2171468534","https://openalex.org/W2243366343","https://openalex.org/W2292869588","https://openalex.org/W2297801999","https://openalex.org/W2754876402","https://openalex.org/W2766718178","https://openalex.org/W2790777705","https://openalex.org/W2794757410","https://openalex.org/W2797713804","https://openalex.org/W2889251616","https://openalex.org/W2906229813","https://openalex.org/W2916041057","https://openalex.org/W2921196518","https://openalex.org/W2964325543","https://openalex.org/W2988766153","https://openalex.org/W3122305330","https://openalex.org/W3122563224","https://openalex.org/W3130367027","https://openalex.org/W3132041644","https://openalex.org/W3162417502","https://openalex.org/W3176368795","https://openalex.org/W3191476277"],"related_works":["https://openalex.org/W2140536630","https://openalex.org/W3195005284","https://openalex.org/W2391730868","https://openalex.org/W4394659737","https://openalex.org/W2759814045","https://openalex.org/W2118055728","https://openalex.org/W4399756845","https://openalex.org/W2736760277","https://openalex.org/W4386940087","https://openalex.org/W4386931226"],"abstract_inverted_index":{"Research":[0],"around":[1],"the":[2,37,52,60,82,103,117,121,126,135,138,148,153,167,178],"process":[3],"of":[4,8,40,84,86,99,120,137,181],"automatic":[5],"price":[6,57],"prediction":[7],"stock":[9,56,87,150],"markets":[10],"indicates":[11],"that":[12,73],"published":[13],"news":[14,34,93,100],"are":[15],"an":[16,26,114],"important":[17],"asset":[18],"to":[19,29,80,95,125],"solve":[20],"this":[21],"problem.We":[22],"further":[23],"elaborate":[24],"on":[25,46,48,116,140,147],"NLP-based":[27],"approach":[28,111],"generate":[30],"industry-specific":[31],"lexicons":[32,79],"from":[33,63,102],"documents":[35],"exploiting":[36],"distributed":[38],"technology":[39],"Apache":[41],"Spark,":[42],"with":[43],"a":[44,49,69,96,141],"focus":[45],"individuating":[47],"day-to-day":[50],"scale":[51],"correlation":[53],"between":[54,170],"significant":[55],"variations":[58],"and":[59,152,172,174],"words":[61],"collected":[62],"press":[64,106],"releases.":[65],"Thereafter":[66],"we":[67,108],"apply":[68],"binary":[70],"classification":[71,162],"algorithm":[72,139],"builds":[74],"upon":[75],"our":[76,110,182],"newly":[77],"generated":[78],"predict":[81],"magnitude":[83],"fluctuation":[85],"market":[88,118,151],"price.":[89],"Subsequently,":[90],"by":[91,112],"processing":[92],"belonging":[94,124],"large":[97],"collection":[98],"articles":[101],"most":[104],"prestigious":[105],"agencies,":[107],"validate":[109],"conducting":[113],"experiment":[115],"history":[119],"US":[122],"companies":[123],"Standard":[127],"&":[128],"Poor":[129],"500":[130],"index.":[131,158],"We":[132],"also":[133],"test":[134],"performance":[136],"multi-lingual":[142],"setting,":[143],"in":[144],"particular":[145],"focusing":[146],"Italian":[149],"Italy":[154],"40":[155],"(FTSE":[156],"MIB)":[157],"Final":[159],"data":[160],"about":[161],"results":[163],"let":[164],"us":[165,176],"assess":[166],"mutual":[168],"dependence":[169],"terms":[171],"prices,":[173],"help":[175],"evaluating":[177],"predictive":[179],"power":[180],"created":[183],"lexicons.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-05-05T00:00:00"}