{"id":"https://openalex.org/W2128051069","doi":"https://doi.org/10.1142/s0218213004001843","title":"A SOFTWARE INFRASTRUCTURE FOR RESEARCH IN TEXTUAL DATA MINING","display_name":"A SOFTWARE INFRASTRUCTURE FOR RESEARCH IN TEXTUAL DATA MINING","publication_year":2004,"publication_date":"2004-12-01","ids":{"openalex":"https://openalex.org/W2128051069","doi":"https://doi.org/10.1142/s0218213004001843","mag":"2128051069"},"language":"en","primary_location":{"id":"doi:10.1142/s0218213004001843","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213004001843","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","raw_type":"journal-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/A5029770342","display_name":"Lars E. Holzman","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"LARS E. HOLZMAN","raw_affiliation_strings":["Computer Science, University of Massachusetts Amherst, MA 01002, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science, University of Massachusetts Amherst, MA 01002, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089216940","display_name":"Todd A. Fisher","orcid":null},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"TODD A. FISHER","raw_affiliation_strings":["Computer Science and Engineering, Lehigh University Bethlehem, PA 18015, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Lehigh University Bethlehem, PA 18015, USA","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090533858","display_name":"Leon M. Galitsky","orcid":null},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"LEON M. GALITSKY","raw_affiliation_strings":["Computer Science and Engineering, Lehigh University, Bethlehem, PA 18015, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Lehigh University, Bethlehem, PA 18015, USA","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068333496","display_name":"April Kontostathis","orcid":null},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"APRIL KONTOSTATHIS","raw_affiliation_strings":["Computer Science and Engineering, Lehigh University, Bethlehem, PA 18015, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Lehigh University, Bethlehem, PA 18015, USA","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011634099","display_name":"William M. Pottenger","orcid":null},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"WILLIAM M. POTTENGER","raw_affiliation_strings":["Computer Science and Engineering, Lehigh University, Bethlehem, PA 18015, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Lehigh University, Bethlehem, PA 18015, USA","institution_ids":["https://openalex.org/I186143895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5029770342"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":3.9453,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.94143634,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"13","issue":"04","first_page":"829","last_page":"849"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9986000061035156,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9986000061035156,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9972000122070312,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8886556625366211},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.7138646245002747},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.663342297077179},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.48483359813690186},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.4725850820541382},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4090529680252075},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3709670305252075},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.36250144243240356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8886556625366211},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.7138646245002747},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.663342297077179},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.48483359813690186},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.4725850820541382},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4090529680252075},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3709670305252075},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.36250144243240356},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218213004001843","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213004001843","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1586759373","https://openalex.org/W2147152072","https://openalex.org/W2466512847"],"related_works":["https://openalex.org/W2798121181","https://openalex.org/W2016805743","https://openalex.org/W4242592912","https://openalex.org/W435830328","https://openalex.org/W2087896742","https://openalex.org/W2328676785","https://openalex.org/W1989025965","https://openalex.org/W2322380964","https://openalex.org/W2317165620","https://openalex.org/W4237443457"],"abstract_inverted_index":{"Few":[0],"tools":[1,33,68],"exist":[2],"that":[3,53,76,139,158,187],"address":[4],"the":[5,10,94,121,141,149,168,193],"challenges":[6],"facing":[7],"researchers":[8,176],"in":[9,60,81,103,126],"Textual":[11,48],"Data":[12,49],"Mining":[13,50],"(TDM)":[14],"field.":[15],"Some":[16],"are":[17,24,35],"too":[18],"specific":[19],"to":[20,65,73,79,177],"their":[21,181],"application,":[22],"or":[23],"prototypes":[25],"not":[26,36,160],"suitable":[27],"for":[28,112,123],"general":[29,32],"use.":[30],"More":[31],"often":[34],"capable":[37],"of":[38,42,85,96,100,108,137,151],"processing":[39,86],"large":[40],"volumes":[41],"data.":[43],"We":[44,153,164],"have":[45,159],"created":[46],"a":[47,61,82,90,135],"Infrastructure":[51],"(TMI)":[52],"incorporates":[54],"both":[55],"existing":[56,171],"and":[57,69,98,179],"new":[58,67],"capabilities":[59],"reusable":[62],"framework":[63],"conducive":[64],"developing":[66],"components.":[70],"TMI":[71,109,169,189],"adheres":[72],"strict":[74],"guidelines":[75],"allow":[77],"it":[78,92],"run":[80],"wide":[83],"range":[84],"environments":[87],"\u2013":[88],"as":[89],"result,":[91],"accommodates":[93],"volume":[95],"computing":[97],"diversity":[99],"research":[101,118],"occurring":[102],"TDM.":[104],"A":[105,143],"unique":[106],"capability":[107],"is":[110,146,190],"support":[111],"optimization.":[113],"This":[114],"facilitates":[115],"text":[116,127],"mining":[117,128],"by":[119],"automating":[120],"search":[122],"optimal":[124],"parameters":[125],"algorithms.":[129],"In":[130],"this":[131],"article":[132],"we":[133],"describe":[134],"number":[136],"applications":[138],"use":[140,150],"TMI.":[142,152],"brief":[144],"tutorial":[145],"provided":[147],"on":[148,192],"present":[154],"several":[155],"novel":[156],"results":[157],"been":[161],"published":[162],"elsewhere.":[163],"also":[165],"discuss":[166],"how":[167],"utilizes":[170],"machine-learning":[172],"libraries,":[173],"thereby":[174],"enabling":[175],"continue":[178],"extend":[180],"endeavors":[182],"with":[183],"minimal":[184],"effort.":[185],"Towards":[186],"end,":[188],"available":[191],"web":[194],"at":[195],".":[196]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
