{"id":"https://openalex.org/W3046807654","doi":"https://doi.org/10.1145/3383583.3398608","title":"Garbage In, Garbage Out? An Empirical Look at Information Richness of LBD Input Types","display_name":"Garbage In, Garbage Out? An Empirical Look at Information Richness of LBD Input Types","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3046807654","doi":"https://doi.org/10.1145/3383583.3398608","mag":"3046807654"},"language":"en","primary_location":{"id":"doi:10.1145/3383583.3398608","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3383583.3398608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020","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/A5086255420","display_name":"Menasha Thilakaratne","orcid":"https://orcid.org/0000-0003-4956-6171"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Menasha Thilakaratne","raw_affiliation_strings":["The University of Adelaide, Adelaide, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006949757","display_name":"Katrina Falkner","orcid":"https://orcid.org/0000-0003-0309-4332"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Katrina Falkner","raw_affiliation_strings":["The University of Adelaide, Adelaide, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058858832","display_name":"Thushari Atapattu","orcid":"https://orcid.org/0000-0002-0632-4482"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Thushari Atapattu","raw_affiliation_strings":["The University of Adelaide, Adelaide, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07103123,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":null,"first_page":"369","last_page":"372"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9980999827384949,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9975000023841858,"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/computer-science","display_name":"Computer science","score":0.8310967087745667},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5935163497924805},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5534131526947021},{"id":"https://openalex.org/keywords/garbage","display_name":"Garbage","score":0.4919528663158417},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4807822108268738},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4488704800605774},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.43638092279434204},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.41948190331459045},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.398016095161438},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2481767237186432},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20289194583892822},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10942164063453674}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8310967087745667},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5935163497924805},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5534131526947021},{"id":"https://openalex.org/C75403996","wikidata":"https://www.wikidata.org/wiki/Q5521979","display_name":"Garbage","level":2,"score":0.4919528663158417},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4807822108268738},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4488704800605774},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.43638092279434204},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.41948190331459045},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.398016095161438},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2481767237186432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20289194583892822},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10942164063453674},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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:10.1145/3383583.3398608","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3383583.3398608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"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":10,"referenced_works":["https://openalex.org/W1748815599","https://openalex.org/W2082997591","https://openalex.org/W2532054931","https://openalex.org/W2774367863","https://openalex.org/W2809634205","https://openalex.org/W2949547296","https://openalex.org/W2951538941","https://openalex.org/W2987066226","https://openalex.org/W4241696300","https://openalex.org/W4244973361"],"related_works":["https://openalex.org/W2612848883","https://openalex.org/W3088744871","https://openalex.org/W4382053766","https://openalex.org/W3035541749","https://openalex.org/W2351860712","https://openalex.org/W4366783061","https://openalex.org/W2354724362","https://openalex.org/W4362509302","https://openalex.org/W4322770937","https://openalex.org/W4226365197"],"abstract_inverted_index":{"Literature-Based":[0],"Discovery":[1],"(LBD)":[2],"which":[3],"is":[4,50,62],"a":[5,108],"sub-discipline":[6],"of":[7,36,41,58,66,91,111,115,118,129],"text":[8],"mining,":[9],"aims":[10],"to":[11,93],"detect":[12],"meaningful":[13],"implicit":[14],"knowledge":[15,48],"linkages":[16],"in":[17,24,135],"digital":[18],"libraries":[19],"that":[20],"have":[21,73],"the":[22,37,42,46,54,67,84,88,95,112,130,136],"potential":[23],"generating":[25],"novel":[26],"research":[27],"hypotheses.":[28],"The":[29],"input":[30,68,76,98,121],"can":[31],"be":[32],"considered":[33],"as":[34,45],"one":[35],"most":[38,96],"critical":[39],"components":[40],"LBD":[43,71,101,120],"process":[44],"entire":[47],"discovery":[49],"solely":[51],"dependent":[52],"on":[53,107],"content":[55],"and":[56],"quality":[57],"input.":[59],"However,":[60],"there":[61],"no":[63],"uniform":[64],"selection":[65],"since":[69],"different":[70,75,116],"studies":[72],"picked":[74],"types":[77],"(e.g.,":[78],"titles,":[79],"abstracts,":[80],"keywords).":[81],"This":[82],"emphasises":[83],"need":[85],"for":[86,100],"assessing":[87],"information":[89,113],"richness":[90,114],"inputs":[92],"decide":[94],"suited":[97],"type":[99],"workflow.":[102],"Therefore,":[103],"this":[104],"study":[105],"focuses":[106],"large-scale":[109],"assessment":[110],"variants":[117],"popular":[119],"types.":[122],"Our":[123],"observations":[124],"are":[125],"consistent":[126],"with":[127],"all":[128],"five":[131],"golden":[132],"test":[133],"cases":[134],"discipline.":[137]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}