{"id":"https://openalex.org/W4221079430","doi":"https://doi.org/10.47989/irpaper917","title":"Investigating the extent to which words or phrases with specific attributes can be retrieved from digital text collections","display_name":"Investigating the extent to which words or phrases with specific attributes can be retrieved from digital text collections","publication_year":2022,"publication_date":"2022-03-12","ids":{"openalex":"https://openalex.org/W4221079430","doi":"https://doi.org/10.47989/irpaper917"},"language":"en","primary_location":{"id":"doi:10.47989/irpaper917","is_oa":true,"landing_page_url":"https://doi.org/10.47989/irpaper917","pdf_url":null,"source":{"id":"https://openalex.org/S4210195660","display_name":"Information Research an international electronic journal","issn_l":"1368-1613","issn":["1368-1613"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310317106","host_organization_name":"University of Bor\u00e5s","host_organization_lineage":["https://openalex.org/P4310317106"],"host_organization_lineage_names":["University of Bor\u00e5s"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Research: an international electronic journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.47989/irpaper917","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051314170","display_name":"Liezl H. Ball","orcid":"https://orcid.org/0000-0002-1483-0780"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liezl Ball","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027072088","display_name":"Theo Bothma","orcid":"https://orcid.org/0000-0001-7850-3263"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Theo Bothma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3705,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84259259,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"27","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.992900013923645,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9926000237464905,"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/metadata","display_name":"Metadata","score":0.9261038303375244},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8342079520225525},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7367373704910278},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.6290066838264465},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.47761696577072144},{"id":"https://openalex.org/keywords/meta-data-services","display_name":"Meta Data Services","score":0.41744309663772583},{"id":"https://openalex.org/keywords/database-catalog","display_name":"Database catalog","score":0.41511207818984985},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.40617862343788147},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07820415496826172}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9261038303375244},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8342079520225525},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7367373704910278},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.6290066838264465},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.47761696577072144},{"id":"https://openalex.org/C136976847","wikidata":"https://www.wikidata.org/wiki/Q6822297","display_name":"Meta Data Services","level":4,"score":0.41744309663772583},{"id":"https://openalex.org/C65610166","wikidata":"https://www.wikidata.org/wiki/Q5227399","display_name":"Database catalog","level":4,"score":0.41511207818984985},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.40617862343788147},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07820415496826172},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.47989/irpaper917","is_oa":true,"landing_page_url":"https://doi.org/10.47989/irpaper917","pdf_url":null,"source":{"id":"https://openalex.org/S4210195660","display_name":"Information Research an international electronic journal","issn_l":"1368-1613","issn":["1368-1613"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310317106","host_organization_name":"University of Bor\u00e5s","host_organization_lineage":["https://openalex.org/P4310317106"],"host_organization_lineage_names":["University of Bor\u00e5s"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Research: an international electronic journal","raw_type":"journal-article"},{"id":"pmh:oai:repository.up.ac.za:2263/90491","is_oa":true,"landing_page_url":"http://hdl.handle.net/2263/90491","pdf_url":"https://repository.up.ac.za/bitstream/2263/90491/1/Ball_Investigating_2022.pdf","source":{"id":"https://openalex.org/S4306401870","display_name":"UpSpace Institutional Repository (University of Pretoria)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I69552723","host_organization_name":"University of Pretoria","host_organization_lineage":["https://openalex.org/I69552723"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.47989/irpaper917","is_oa":true,"landing_page_url":"https://doi.org/10.47989/irpaper917","pdf_url":null,"source":{"id":"https://openalex.org/S4210195660","display_name":"Information Research an international electronic journal","issn_l":"1368-1613","issn":["1368-1613"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310317106","host_organization_name":"University of Bor\u00e5s","host_organization_lineage":["https://openalex.org/P4310317106"],"host_organization_lineage_names":["University of Bor\u00e5s"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Research: an international electronic journal","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W42994758","https://openalex.org/W68441731","https://openalex.org/W1579448319","https://openalex.org/W1594247117","https://openalex.org/W1824941666","https://openalex.org/W1912336655","https://openalex.org/W1979921636","https://openalex.org/W1982766738","https://openalex.org/W2002602589","https://openalex.org/W2006873532","https://openalex.org/W2019096529","https://openalex.org/W2095503871","https://openalex.org/W2106279089","https://openalex.org/W2127160125","https://openalex.org/W2140352991","https://openalex.org/W2275957045","https://openalex.org/W2295189257","https://openalex.org/W2325553602","https://openalex.org/W2326713822","https://openalex.org/W2409809551","https://openalex.org/W2461998661","https://openalex.org/W2462248047","https://openalex.org/W2583401130","https://openalex.org/W2627405664","https://openalex.org/W2768817266","https://openalex.org/W2804512604","https://openalex.org/W2806849745","https://openalex.org/W2886389738","https://openalex.org/W3082037758","https://openalex.org/W3087388925","https://openalex.org/W3101412767","https://openalex.org/W3197053064","https://openalex.org/W4230450052","https://openalex.org/W4249238571"],"related_works":["https://openalex.org/W2374379029","https://openalex.org/W2391915033","https://openalex.org/W1503116306","https://openalex.org/W2360250168","https://openalex.org/W2527789274","https://openalex.org/W2354596657","https://openalex.org/W1504835998","https://openalex.org/W2394393789","https://openalex.org/W4299935056","https://openalex.org/W1935670680"],"abstract_inverted_index":{"Introduction.":[0],"Digital":[1],"text":[2,41,164],"collections":[3,42],"are":[4,27,71,85,106,128],"increasingly":[5],"being":[6],"used.":[7],"Various":[8],"tools":[9,36,97,124,173],"have":[10,101],"been":[11,102],"developed":[12],"to":[13,16,38,45,47,67,91,112,115,131,179],"allow":[14,51],"researchers":[15,152],"explore":[17,39],"such":[18],"collections.":[19,165],"Enhanced":[20],"retrieval":[21,54,182],"will":[22],"be":[23,170,195],"possible":[24,111],"if":[25],"texts":[26],"encoded":[28],"with":[29,59,98,159,187],"granular":[30],"metadata.":[31,120],"Method.":[32],"A":[33],"selection":[34],"of":[35,55,122,135,145,150,183],"used":[37],"digital":[40,163],"was":[43],"evaluated":[44,65],"determine":[46],"what":[48],"extent":[49],"they":[50],"for":[52],"the":[53,68,74,76,80,83,88,93,123,146,181],"words":[56,156,184],"or":[57,117,143,157,185],"phrases":[58,158,186],"specific":[60,160,188],"attributes.":[61],"Analysis.":[62],"Tools":[63],"were":[64],"according":[66,114],"metadata":[69,136,168,178],"that":[70,126,174],"available":[72],"in":[73,79,190],"data,":[75,151],"search":[77,113],"options":[78,130],"tool,":[81],"how":[82],"results":[84],"displayed,":[86],"and":[87,137,148,172],"expertise":[89,142],"required":[90],"use":[92],"tool.":[94],"Results.":[95],"Many":[96],"powerful":[99],"functions":[100],"developed.":[103,196],"However,":[104],"there":[105,127],"limitations.":[107],"It":[108],"is":[109],"not":[110],"semantics":[116],"in-text":[118],"bibliographic":[119],"Analysis":[121],"revealed":[125],"limited":[129],"combine":[132],"multiple":[133],"levels":[134],"typically,":[138],"without":[139],"some":[140],"programming":[141],"knowledge":[144],"structure":[147],"encoding":[149],"cannot":[153],"currently":[154],"retrieve":[155],"attributes":[161,189],"from":[162],"Conclusions.":[166],"Granular":[167],"should":[169,194],"identified,":[171],"can":[175],"utilise":[176],"these":[177],"enable":[180],"an":[191],"intuitive":[192],"manner":[193]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2022-04-03T00:00:00"}
