{"id":"https://openalex.org/W3007627427","doi":"https://doi.org/10.1109/bigdata47090.2019.9006368","title":"FinDX: A Versatile, Low-Resource Approach to Financial Website Classification","display_name":"FinDX: A Versatile, Low-Resource Approach to Financial Website Classification","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007627427","doi":"https://doi.org/10.1109/bigdata47090.2019.9006368","mag":"3007627427"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata47090.2019.9006368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 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/A5034648031","display_name":"Alissa Ostapenko","orcid":null},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alissa Ostapenko","raw_affiliation_strings":["Computer Science Department, Worcester Polytechnic Institute, Worcester MA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Worcester Polytechnic Institute, Worcester MA, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008363462","display_name":"Rodica Neamtu","orcid":"https://orcid.org/0000-0003-4647-5610"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rodica Neamtu","raw_affiliation_strings":["Computer Science Department, Worcester Polytechnic Institute, Worcester MA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Worcester Polytechnic Institute, Worcester MA, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061748346","display_name":"Frazer Anderson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frazer Anderson","raw_affiliation_strings":["Investment Analyst Vestigo Ventures, Cambridge MA, USA"],"affiliations":[{"raw_affiliation_string":"Investment Analyst Vestigo Ventures, Cambridge MA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034648031"],"corresponding_institution_ids":["https://openalex.org/I107077323"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27933673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"5559","last_page":"5568"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11995","display_name":"FinTech, Crowdfunding, Digital Finance","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11995","display_name":"FinTech, Crowdfunding, Digital Finance","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9811000227928162,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9794999957084656,"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/computer-science","display_name":"Computer science","score":0.7132172584533691},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.6277649402618408},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6029993295669556},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5242871642112732},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5231415033340454},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.47595474123954773},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4350546896457672},{"id":"https://openalex.org/keywords/web-resource","display_name":"Web resource","score":0.4320544898509979},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.4233793318271637},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37029722332954407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3388729989528656},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3313601613044739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7132172584533691},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.6277649402618408},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6029993295669556},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5242871642112732},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5231415033340454},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.47595474123954773},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4350546896457672},{"id":"https://openalex.org/C65603577","wikidata":"https://www.wikidata.org/wiki/Q3427877","display_name":"Web resource","level":2,"score":0.4320544898509979},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.4233793318271637},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37029722332954407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3388729989528656},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3313601613044739},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata47090.2019.9006368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"mag:3043803734","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002283249653426","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W46659105","https://openalex.org/W1482260847","https://openalex.org/W1532325895","https://openalex.org/W1543345473","https://openalex.org/W1596622341","https://openalex.org/W2013316690","https://openalex.org/W2058049637","https://openalex.org/W2059586463","https://openalex.org/W2076008912","https://openalex.org/W2101234009","https://openalex.org/W2104933073","https://openalex.org/W2143017621","https://openalex.org/W2148143831","https://openalex.org/W2149684865","https://openalex.org/W2153579005","https://openalex.org/W2254186207","https://openalex.org/W2408663442","https://openalex.org/W2521200999","https://openalex.org/W2544700275","https://openalex.org/W2766389674","https://openalex.org/W2903172129","https://openalex.org/W2912364678","https://openalex.org/W2914634430","https://openalex.org/W2915736414","https://openalex.org/W2953320089","https://openalex.org/W2963042536","https://openalex.org/W3015720892","https://openalex.org/W4242121546","https://openalex.org/W4293713156","https://openalex.org/W4294170691","https://openalex.org/W6635644450","https://openalex.org/W6675354045","https://openalex.org/W6675634716","https://openalex.org/W6682691769","https://openalex.org/W6764970959","https://openalex.org/W6868376916"],"related_works":["https://openalex.org/W3005260231","https://openalex.org/W4226079483","https://openalex.org/W3109858739","https://openalex.org/W2183593492","https://openalex.org/W2794831687","https://openalex.org/W4285048456","https://openalex.org/W2073780884","https://openalex.org/W2066309116","https://openalex.org/W2378232036","https://openalex.org/W4313495655"],"abstract_inverted_index":{"The":[0],"World":[1],"Wide":[2],"Web":[3],"provides":[4],"an":[5],"excellent":[6],"platform":[7],"for":[8,59,64,171],"investors":[9],"to":[10,25,29,123,159],"discover":[11],"new":[12],"partnership":[13],"opportunities":[14],"with":[15],"a":[16,57,77,113,125,146],"variety":[17],"of":[18,73,98,142,149],"companies.":[19],"Analysts":[20],"can":[21],"categorize":[22],"websites":[23,35],"according":[24],"their":[26],"business":[27,143,161],"domains":[28],"retain":[30],"relevant":[31,89],"investment":[32],"opportunities.":[33],"Classifying":[34],"manually":[36],"is":[37,76,156,164],"too":[38],"expensive":[39],"and":[40,88,105,163],"time-consuming;":[41],"thus,":[42],"automatic":[43,60],"classification":[44,63,136],"tools":[45],"are":[46],"necessary.":[47],"In":[48,151],"this":[49],"paper,":[50],"we":[51,111],"present":[52],"FinDX":[53,132,169],"(Financial":[54],"Data":[55],"EXploration),":[56],"tool":[58,155],"website":[61,127],"content":[62],"the":[65,71,85,93,103],"financial":[66],"technology":[67],"(fintech)":[68],"domain.":[69],"At":[70],"core":[72],"our":[74,153],"system":[75],"keyword-based":[78],"web":[79],"crawler":[80],"that":[81],"extracts":[82],"text":[83,104],"from":[84],"landing":[86],"page":[87],"subpages,":[90],"such":[91],"as":[92,128],"About":[94],"or":[95,119,130],"Product":[96],"pages":[97],"company":[99,126],"websites.":[100],"After":[101],"cleaning":[102],"filtering":[106],"it":[107],"using":[108],"part-of-speech":[109],"tagging,":[110],"use":[112,172],"Linear":[114],"Support":[115],"Vector":[116],"Machine":[117],"(SVM)":[118],"Multilayer":[120],"Perceptron":[121],"(MLP)":[122],"classify":[124],"fintech":[129],"non-fintech.":[131],"achieves":[133],"high":[134],"binary":[135],"accuracy":[137],"on":[138],"two":[139],"different":[140],"datasets":[141],"websites,":[144],"attaining":[145],"maximal":[147],"F-score":[148],"96%.":[150],"addition,":[152],"flexible":[154],"easily":[157],"adaptable":[158],"any":[160],"domain":[162],"not":[165],"resource-expensive.":[166],"This":[167],"makes":[168],"ideal":[170],"in":[173],"startup":[174],"environments.":[175]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}