{"id":"https://openalex.org/W4250426774","doi":"https://doi.org/10.1109/jcdl.2014.6970163","title":"The anatomy of a search and mining system for digital humanities","display_name":"The anatomy of a search and mining system for digital humanities","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W4250426774","doi":"https://doi.org/10.1109/jcdl.2014.6970163"},"language":"en","primary_location":{"id":"doi:10.1109/jcdl.2014.6970163","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcdl.2014.6970163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Joint Conference on Digital Libraries","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/A5102050264","display_name":"Martyn Harris","orcid":null},"institutions":[{"id":"https://openalex.org/I98259816","display_name":"Birkbeck, University of London","ror":"https://ror.org/02mb95055","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I98259816"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Martyn Harris","raw_affiliation_strings":["Department of Computer Science Birkbeck, University of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science Birkbeck, University of London, London, UK","institution_ids":["https://openalex.org/I98259816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015725705","display_name":"Mark Levene","orcid":"https://orcid.org/0000-0001-8632-4732"},"institutions":[{"id":"https://openalex.org/I98259816","display_name":"Birkbeck, University of London","ror":"https://ror.org/02mb95055","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I98259816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark Levene","raw_affiliation_strings":["Department of Computer Science Birkbeck, University of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science Birkbeck, University of London, London, UK","institution_ids":["https://openalex.org/I98259816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015784640","display_name":"Dell Zhang","orcid":"https://orcid.org/0000-0002-8774-3725"},"institutions":[{"id":"https://openalex.org/I98259816","display_name":"Birkbeck, University of London","ror":"https://ror.org/02mb95055","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I98259816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dell Zhang","raw_affiliation_strings":["Department of Computer Science Birkbeck, University of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science Birkbeck, University of London, London, UK","institution_ids":["https://openalex.org/I98259816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111310912","display_name":"Dan Levene","orcid":null},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dan Levene","raw_affiliation_strings":["History, School of Humanities, University of Southampton, Southampton, UK"],"affiliations":[{"raw_affiliation_string":"History, School of Humanities, University of Southampton, Southampton, UK","institution_ids":["https://openalex.org/I43439940"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102050264"],"corresponding_institution_ids":["https://openalex.org/I98259816"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.32747997,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"6","issue":null,"first_page":"165","last_page":"168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994999766349792,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9994999766349792,"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":0.9991999864578247,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.71614009141922},{"id":"https://openalex.org/keywords/genizah","display_name":"Genizah","score":0.6855536103248596},{"id":"https://openalex.org/keywords/digital-humanities","display_name":"Digital humanities","score":0.5055153369903564},{"id":"https://openalex.org/keywords/unicode","display_name":"Unicode","score":0.4962928891181946},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4512457549571991},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.41684162616729736},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4158734083175659},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39700064063072205},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3899398446083069},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.346602201461792},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.26306605339050293},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.13156354427337646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.71614009141922},{"id":"https://openalex.org/C109901321","wikidata":"https://www.wikidata.org/wiki/Q855266","display_name":"Genizah","level":3,"score":0.6855536103248596},{"id":"https://openalex.org/C24351657","wikidata":"https://www.wikidata.org/wiki/Q1026962","display_name":"Digital humanities","level":2,"score":0.5055153369903564},{"id":"https://openalex.org/C500551929","wikidata":"https://www.wikidata.org/wiki/Q8819","display_name":"Unicode","level":2,"score":0.4962928891181946},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4512457549571991},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.41684162616729736},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4158734083175659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39700064063072205},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3899398446083069},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.346602201461792},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.26306605339050293},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.13156354427337646},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C150152722","wikidata":"https://www.wikidata.org/wiki/Q9268","display_name":"Judaism","level":2,"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jcdl.2014.6970163","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcdl.2014.6970163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Joint Conference on Digital Libraries","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8700000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W938539187","https://openalex.org/W1968960207","https://openalex.org/W2003549201","https://openalex.org/W2027447543","https://openalex.org/W2146950091","https://openalex.org/W2398269865","https://openalex.org/W4213009331","https://openalex.org/W4301029683","https://openalex.org/W6634858473","https://openalex.org/W6712277271"],"related_works":["https://openalex.org/W2996910546","https://openalex.org/W1953677193","https://openalex.org/W1423973944","https://openalex.org/W2158203244","https://openalex.org/W2256003138","https://openalex.org/W2319259419","https://openalex.org/W4387405973","https://openalex.org/W4234580134","https://openalex.org/W2316814541","https://openalex.org/W2209478830"],"abstract_inverted_index":{"Samtla":[0,81,126],"(Search":[1],"And":[2],"Mining":[3],"Tools":[4],"with":[5,17],"Linguistic":[6],"Analysis)":[7],"is":[8,96],"an":[9],"online":[10],"integrated":[11],"research":[12,36],"environment":[13],"designed":[14],"in":[15,29,50],"collaboration":[16],"historians":[18],"and":[19,53,69,85,127],"linguists":[20],"to":[21,65,93],"facilitate":[22],"the":[23,35,40,45,76,83,122],"study":[24],"of":[25,37,56,79,87,109,125],"digitised":[26],"texts":[27,59],"written":[28],"any":[30],"language.":[31],"It":[32],"currently":[33],"supports":[34],"two":[38],"corpora:":[39],"Genizah":[41,47],"collection":[42,55],"held":[43],"by":[44],"Taylor-Schechter":[46],"Research":[48],"Unit":[49],"Cambridge":[51],"University,":[52],"a":[54,100,110],"Aramaic":[57],"incantation":[58],"from":[60],"late":[61],"antiquity.":[62],"In":[63],"contrast":[64],"standard":[66],"search":[67],"engines":[68],"text":[70,89],"mining":[71],"systems":[72],"that":[73],"rely":[74],"on":[75,107],"bag-of-words":[77],"representation":[78],"text,":[80],"provides":[82],"retrieval":[84],"discovery":[86],"fuzzy":[88],"patterns/motifs":[90],"(aka":[91],"\"formulae\"":[92],"historians),":[94],"which":[95],"achieved":[97],"through":[98],"applying":[99],"character-based":[101],"n-gram":[102],"statistical":[103],"language":[104],"model":[105],"built":[106],"top":[108],"powerful":[111],"generalised":[112],"suffix":[113],"tree":[114],"data":[115],"structure.":[116],"This":[117],"paper":[118],"brie":[119],"y":[120],"describes":[121],"major":[123],"components":[124],"their":[128],"underlying":[129],"techniques.":[130]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
