{"id":"https://openalex.org/W3082684473","doi":"https://doi.org/10.1140/epjds/s13688-020-00244-9","title":"Enriching feature engineering for short text samples by language time series analysis","display_name":"Enriching feature engineering for short text samples by language time series analysis","publication_year":2020,"publication_date":"2020-08-31","ids":{"openalex":"https://openalex.org/W3082684473","doi":"https://doi.org/10.1140/epjds/s13688-020-00244-9","mag":"3082684473"},"language":"en","primary_location":{"id":"doi:10.1140/epjds/s13688-020-00244-9","is_oa":true,"landing_page_url":"https://doi.org/10.1140/epjds/s13688-020-00244-9","pdf_url":"https://epjdatascience.springeropen.com/track/pdf/10.1140/epjds/s13688-020-00244-9","source":{"id":"https://openalex.org/S2504380752","display_name":"EPJ Data Science","issn_l":"2193-1127","issn":["2193-1127"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EPJ Data Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://epjdatascience.springeropen.com/track/pdf/10.1140/epjds/s13688-020-00244-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084811163","display_name":"Yichen Tang","orcid":"https://orcid.org/0000-0002-9081-2736"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Yichen Tang","raw_affiliation_strings":["Department of Electrical, Computer, and Software Engineering, University of Auckland, 20 Symonds St, 1010, Auckland, New Zealand","Department of Engineering Science, University of Auckland, 70 Symonds St, 1010, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer, and Software Engineering, University of Auckland, 20 Symonds St, 1010, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]},{"raw_affiliation_string":"Department of Engineering Science, University of Auckland, 70 Symonds St, 1010, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039326697","display_name":"Kelly Blincoe","orcid":"https://orcid.org/0000-0003-4092-9706"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Kelly Blincoe","raw_affiliation_strings":["Department of Electrical, Computer, and Software Engineering, University of Auckland, 20 Symonds St, 1010, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer, and Software Engineering, University of Auckland, 20 Symonds St, 1010, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000654559","display_name":"Andreas W. Kempa-Liehr","orcid":"https://orcid.org/0000-0001-5558-0573"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Andreas W. Kempa-Liehr","raw_affiliation_strings":["Department of Engineering Science, University of Auckland, 70 Symonds St, 1010, Auckland, New Zealand"],"raw_orcid":"https://orcid.org/0000-0001-5558-0573","affiliations":[{"raw_affiliation_string":"Department of Engineering Science, University of Auckland, 70 Symonds St, 1010, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5000654559"],"corresponding_institution_ids":["https://openalex.org/I154130895"],"apc_list":{"value":1690,"currency":"USD","value_usd":1690},"apc_paid":{"value":1690,"currency":"USD","value_usd":1690},"fwci":0.8044,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79448801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"9","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9988999962806702,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9930999875068665,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9692999720573425,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.7894119620323181},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7626233100891113},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7351849675178528},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6522014141082764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6294565796852112},{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.5549024939537048},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.541223406791687},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.48809778690338135},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.4817100167274475},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.47476673126220703},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46930789947509766},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4293718934059143},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4112822115421295},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3480186462402344},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3161686062812805},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.14281824231147766},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10323944687843323}],"concepts":[{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.7894119620323181},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7626233100891113},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7351849675178528},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6522014141082764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6294565796852112},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.5549024939537048},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.541223406791687},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.48809778690338135},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.4817100167274475},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.47476673126220703},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46930789947509766},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4293718934059143},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4112822115421295},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3480186462402344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3161686062812805},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.14281824231147766},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10323944687843323},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1140/epjds/s13688-020-00244-9","is_oa":true,"landing_page_url":"https://doi.org/10.1140/epjds/s13688-020-00244-9","pdf_url":"https://epjdatascience.springeropen.com/track/pdf/10.1140/epjds/s13688-020-00244-9","source":{"id":"https://openalex.org/S2504380752","display_name":"EPJ Data Science","issn_l":"2193-1127","issn":["2193-1127"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EPJ Data Science","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:e7c7d266620c4244a1c7a9aa14347cae","is_oa":true,"landing_page_url":"https://doaj.org/article/e7c7d266620c4244a1c7a9aa14347cae","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EPJ Data Science, Vol 9, Iss 1, Pp 1-59 (2020)","raw_type":"article"},{"id":"pmh:oai:researchspace.auckland.ac.nz:2292/53280","is_oa":true,"landing_page_url":"https://hdl.handle.net/2292/53280","pdf_url":null,"source":{"id":"https://openalex.org/S7407055463","display_name":"ResearchSpace (University of Auckland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I154130895","host_organization_name":"University of Auckland","host_organization_lineage":["https://openalex.org/I154130895"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1140/epjds/s13688-020-00244-9","is_oa":true,"landing_page_url":"https://doi.org/10.1140/epjds/s13688-020-00244-9","pdf_url":"https://epjdatascience.springeropen.com/track/pdf/10.1140/epjds/s13688-020-00244-9","source":{"id":"https://openalex.org/S2504380752","display_name":"EPJ Data Science","issn_l":"2193-1127","issn":["2193-1127"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EPJ Data Science","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320801","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3082684473.pdf","grobid_xml":"https://content.openalex.org/works/W3082684473.grobid-xml"},"referenced_works_count":84,"referenced_works":["https://openalex.org/W6436850","https://openalex.org/W16794263","https://openalex.org/W1498437823","https://openalex.org/W1502957213","https://openalex.org/W1521626219","https://openalex.org/W1547032355","https://openalex.org/W1550661103","https://openalex.org/W1560013842","https://openalex.org/W1572786359","https://openalex.org/W1606247040","https://openalex.org/W1822708450","https://openalex.org/W1918540025","https://openalex.org/W1966626540","https://openalex.org/W1972978214","https://openalex.org/W1974828111","https://openalex.org/W1976095474","https://openalex.org/W1991638834","https://openalex.org/W2004910511","https://openalex.org/W2007438860","https://openalex.org/W2012761320","https://openalex.org/W2017295327","https://openalex.org/W2025882237","https://openalex.org/W2028243078","https://openalex.org/W2032170121","https://openalex.org/W2036991663","https://openalex.org/W2037030737","https://openalex.org/W2044605773","https://openalex.org/W2055699824","https://openalex.org/W2064604759","https://openalex.org/W2072356720","https://openalex.org/W2072828027","https://openalex.org/W2075714842","https://openalex.org/W2087768967","https://openalex.org/W2090624938","https://openalex.org/W2095069785","https://openalex.org/W2100796029","https://openalex.org/W2101234009","https://openalex.org/W2104595931","https://openalex.org/W2110065044","https://openalex.org/W2121904901","https://openalex.org/W2138550913","https://openalex.org/W2153475516","https://openalex.org/W2154977593","https://openalex.org/W2165281381","https://openalex.org/W2165431734","https://openalex.org/W2167183611","https://openalex.org/W2171951705","https://openalex.org/W2177266839","https://openalex.org/W2217402295","https://openalex.org/W2247436149","https://openalex.org/W2295598076","https://openalex.org/W2342249984","https://openalex.org/W2468893743","https://openalex.org/W2508310662","https://openalex.org/W2536130102","https://openalex.org/W2545001194","https://openalex.org/W2555077524","https://openalex.org/W2557287083","https://openalex.org/W2585078266","https://openalex.org/W2594517479","https://openalex.org/W2594788739","https://openalex.org/W2613184892","https://openalex.org/W2759690896","https://openalex.org/W2760178629","https://openalex.org/W2793223974","https://openalex.org/W2793650116","https://openalex.org/W2802314367","https://openalex.org/W2805083960","https://openalex.org/W2887994137","https://openalex.org/W2889194293","https://openalex.org/W2889340004","https://openalex.org/W2912409473","https://openalex.org/W2963579919","https://openalex.org/W2977215731","https://openalex.org/W3003257820","https://openalex.org/W3021971632","https://openalex.org/W3098115713","https://openalex.org/W3099194334","https://openalex.org/W3102476541","https://openalex.org/W3103145119","https://openalex.org/W3121961986","https://openalex.org/W4250089123","https://openalex.org/W4252684946","https://openalex.org/W4292156489"],"related_works":["https://openalex.org/W2970530566","https://openalex.org/W2967478618","https://openalex.org/W2997152889","https://openalex.org/W4385572700","https://openalex.org/W4388335561","https://openalex.org/W2750075801","https://openalex.org/W3164948662","https://openalex.org/W3153597579","https://openalex.org/W4385336128","https://openalex.org/W4205436246"],"abstract_inverted_index":{"Abstract":[0],"In":[1],"this":[2],"case":[3],"study,":[4],"we":[5],"are":[6],"extending":[7],"feature":[8,38,109,145,203,223],"engineering":[9,39,146,204,224],"approaches":[10,186,227],"for":[11,148,187,209,238],"short":[12,149],"text":[13,45,66,93,123,150],"samples":[14,46],"by":[15,84,103],"integrating":[16],"techniques":[17],"which":[18,56,73,134],"have":[19,192],"been":[20],"introduced":[21],"in":[22],"the":[23,36,44,62,85,88,92,158,164,172,193,197,201,221],"context":[24],"of":[25,35,61,87,105,126,214],"time":[26,71,81,98,107,113,175,229],"series":[27,99,108,114,176,230],"classification":[28,198,231],"and":[29,49,80,116,163,191,212,232],"signal":[30,117],"processing.":[31,118],"The":[32,95,143,217],"general":[33],"idea":[34],"presented":[37,218],"approach":[40,120,205],"is":[41,74,82,152],"to":[42,53,130,154,195],"tokenize":[43],"under":[47],"consideration":[48],"map":[50],"each":[51,65,122],"token":[52,90],"a":[54,58,69,234],"number,":[55],"measures":[57],"specific":[59],"property":[60],"token.":[63],"Consequently,":[64],"sample":[67,124],"becomes":[68],"language":[70,97,174,189],"series,":[72],"generated":[75],"from":[76,112,228],"consecutively":[77],"emitted":[78],"tokens,":[79],"represented":[83],"position":[86],"respective":[89],"within":[91],"sample.":[94],"resulting":[96],"can":[100,135,178,206],"be":[101,136,179,207],"characterised":[102],"collections":[104],"established":[106],"extraction":[110],"algorithms":[111],"analysis":[115],"This":[119],"maps":[121],"(irrespective":[125],"its":[127],"original":[128],"length)":[129],"3970":[131],"stylometric":[132,215],"features,":[133],"analysed":[137],"with":[138,182],"standard":[139,183],"statistical":[140,235],"learning":[141,185],"methodologies.":[142],"proposed":[144],"technique":[147],"data":[151,161,167],"applied":[153],"two":[155],"different":[156],"corpora:":[157],"Federalist":[159],"Papers":[160],"set":[162],"Spooky":[165],"Books":[166],"set.":[168],"We":[169],"demonstrate":[170],"that":[171],"extracted":[173],"features":[177],"successfully":[180],"combined":[181],"machine":[184],"natural":[188],"processing":[190],"potential":[194],"improve":[196],"performance.":[199],"Furthermore,":[200],"suggested":[202],"used":[208],"visualizing":[210],"differences":[211],"commonalities":[213],"features.":[216],"framework":[219],"models":[220],"systematic":[222],"based":[225],"on":[226],"develops":[233],"testing":[236],"methodology":[237],"multi-classification":[239],"problems.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2020-09-08T00:00:00"}