{"id":"https://openalex.org/W3080685974","doi":"https://doi.org/10.1145/3394486.3406465","title":"Scientific Text Mining and Knowledge Graphs","display_name":"Scientific Text Mining and Knowledge Graphs","publication_year":2020,"publication_date":"2020-08-20","ids":{"openalex":"https://openalex.org/W3080685974","doi":"https://doi.org/10.1145/3394486.3406465","mag":"3080685974"},"language":"en","primary_location":{"id":"doi:10.1145/3394486.3406465","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3406465","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3406465","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3406465","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074821819","display_name":"Meng Jiang","orcid":"https://orcid.org/0000-0002-3009-519X"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Meng Jiang","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039500313","display_name":"Jingbo Shang","orcid":"https://orcid.org/0000-0002-7249-4404"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingbo Shang","raw_affiliation_strings":["University of California, San Diego, La Jolla, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5074821819"],"corresponding_institution_ids":["https://openalex.org/I107639228"],"apc_list":null,"apc_paid":null,"fwci":0.4078,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.69825606,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3537","last_page":"3538"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9976000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7423380017280579},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.5877145528793335},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5729964971542358},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.5711455941200256},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.53752601146698},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.5063925981521606},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.492998331785202},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4829370379447937},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.45656734704971313},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.4214399755001068},{"id":"https://openalex.org/keywords/sociology-of-scientific-knowledge","display_name":"Sociology of scientific knowledge","score":0.41047239303588867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30263376235961914},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.27896273136138916},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1958770751953125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7423380017280579},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.5877145528793335},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5729964971542358},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.5711455941200256},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.53752601146698},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.5063925981521606},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.492998331785202},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4829370379447937},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.45656734704971313},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.4214399755001068},{"id":"https://openalex.org/C195732255","wikidata":"https://www.wikidata.org/wiki/Q981008","display_name":"Sociology of scientific knowledge","level":2,"score":0.41047239303588867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30263376235961914},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.27896273136138916},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1958770751953125},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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:10.1145/3394486.3406465","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3406465","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3406465","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3394486.3406465","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3406465","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3406465","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1393155390","display_name":"SHF: Medium: Collaborative Research: Semantically-Enhanced Software Traceability for Supporting Human-Centric Tasks","funder_award_id":"1901059","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4512456570","display_name":null,"funder_award_id":"IIS-1849816","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7526817510","display_name":null,"funder_award_id":"1849816","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3080685974.pdf","grobid_xml":"https://content.openalex.org/works/W3080685974.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2593560537","https://openalex.org/W2595918108","https://openalex.org/W2600322774","https://openalex.org/W2883559670","https://openalex.org/W2891383691","https://openalex.org/W2911489562","https://openalex.org/W2931198394","https://openalex.org/W2945165791","https://openalex.org/W2945924302","https://openalex.org/W2963670884","https://openalex.org/W2963718112","https://openalex.org/W2964175037","https://openalex.org/W2964560812","https://openalex.org/W2970224261","https://openalex.org/W2970771982","https://openalex.org/W2971039193","https://openalex.org/W2988402184","https://openalex.org/W2998486497","https://openalex.org/W3005235747","https://openalex.org/W3034306482","https://openalex.org/W3034588688","https://openalex.org/W3035458998","https://openalex.org/W3099053576","https://openalex.org/W6601846001","https://openalex.org/W6834284007"],"related_works":["https://openalex.org/W3203889067","https://openalex.org/W3184725726","https://openalex.org/W2378793138","https://openalex.org/W2019158987","https://openalex.org/W4292070284","https://openalex.org/W4319071221","https://openalex.org/W4313174091","https://openalex.org/W1516746680","https://openalex.org/W4313219769","https://openalex.org/W2788641582"],"abstract_inverted_index":{"Unstructured":[0],"scientific":[1,56,109,125],"text,":[2],"in":[3,33,93,149],"various":[4],"forms":[5,60],"of":[6,22,101],"textual":[7],"artifacts,":[8],"including":[9],"manuscripts,":[10],"publications,":[11],"patents,":[12],"and":[13,28,38,78,91,113,122,133],"proposals,":[14],"is":[15,48],"used":[16],"to":[17,49],"store":[18],"the":[19,34,55],"tremendous":[20],"wealth":[21],"knowledge":[23,64,126],"discovered":[24],"after":[25],"weeks,":[26],"months,":[27],"years,":[29],"developing":[30],"hypotheses,":[31],"working":[32],"lab":[35],"or":[36],"clinic,":[37],"analyzing":[39],"results.":[40],"A":[41],"grand":[42],"challenge":[43],"on":[44,73,88,139,147],"data":[45],"mining":[46,103],"research":[47,90],"develop":[50],"effective":[51],"methods":[52,104,119,144],"for":[53,75,128],"transforming":[54],"text":[57,102,148],"into":[58],"well-structured":[59],"(e.g.,":[61,151],"ontology,":[62],"taxonomy,":[63],"graphs),":[65],"so":[66],"that":[67,105,120,145],"machine":[68],"intelligent":[69],"systems":[70],"can":[71],"build":[72],"them":[74],"hypothesis":[76],"generation":[77],"validation.":[79],"In":[80],"this":[81,94],"tutorial,":[82],"we":[83,97,117,137],"provide":[84],"a":[85,99],"comprehensive":[86],"overview":[87],"recent":[89],"development":[92],"direction.":[95],"First,":[96],"introduce":[98],"series":[100],"extract":[106],"phrases,":[107],"entities,":[108],"concepts,":[110],"relations,":[111],"claims,":[112],"experimental":[114],"evidence.":[115],"Then":[116],"discuss":[118],"construct":[121],"learn":[123],"from":[124],"graphs":[127],"accurate":[129],"search,":[130],"document":[131],"classification,":[132],"exploratory":[134],"analysis.":[135],"Specifically,":[136],"focus":[138],"scalable,":[140],"effective,":[141],"weakly":[142],"supervised":[143],"work":[146],"sciences":[150],"chemistry,":[152],"biology).":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}