{"id":"https://openalex.org/W4290874877","doi":"https://doi.org/10.1145/3534678.3542606","title":"New Frontiers of Scientific Text Mining","display_name":"New Frontiers of Scientific Text Mining","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4290874877","doi":"https://doi.org/10.1145/3534678.3542606"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3542606","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3542606","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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/A5100328989","display_name":"Xuan Wang","orcid":"https://orcid.org/0000-0002-1381-8958"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xuan Wang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020850575","display_name":"Hongwei Wang","orcid":"https://orcid.org/0000-0002-6611-7813"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongwei Wang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075033889","display_name":"Heng Ji","orcid":"https://orcid.org/0000-0002-0464-7966"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heng Ji","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019539533","display_name":"Jiawei Han","orcid":"https://orcid.org/0000-0002-3629-2696"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiawei Han","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100328989"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.8818,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69699367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4832","last_page":"4833"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9998000264167786,"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":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9941999912261963,"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":0.9932000041007996,"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":0.7173007130622864},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6161124110221863},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6155659556388855},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.5782716274261475},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5566498041152954},{"id":"https://openalex.org/keywords/biomedical-text-mining","display_name":"Biomedical text mining","score":0.5318175554275513},{"id":"https://openalex.org/keywords/scientific-literature","display_name":"Scientific literature","score":0.5304006338119507},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5159293413162231},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5109333395957947},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4872826337814331},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.42852064967155457},{"id":"https://openalex.org/keywords/scientific-discovery","display_name":"Scientific discovery","score":0.4275122582912445},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3812011182308197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20994746685028076},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.18932443857192993},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.18554753065109253}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7173007130622864},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6161124110221863},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6155659556388855},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.5782716274261475},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5566498041152954},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.5318175554275513},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.5304006338119507},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5159293413162231},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5109333395957947},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4872826337814331},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42852064967155457},{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.4275122582912445},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3812011182308197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20994746685028076},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.18932443857192993},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.18554753065109253},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3534678.3542606","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3542606","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8399999737739563}],"awards":[{"id":"https://openalex.org/G1472423617","display_name":null,"funder_award_id":"FA8750-19-2-1004","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G2063335192","display_name":null,"funder_award_id":"2019897","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"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1932742904","https://openalex.org/W1981208470","https://openalex.org/W2053673723","https://openalex.org/W2145870108","https://openalex.org/W2521367263","https://openalex.org/W2777416523","https://openalex.org/W2804613706","https://openalex.org/W2888645935","https://openalex.org/W2913903407","https://openalex.org/W2970813009","https://openalex.org/W3005056635","https://openalex.org/W3038057640","https://openalex.org/W3121433727","https://openalex.org/W3139281401","https://openalex.org/W3165523615","https://openalex.org/W3167906655","https://openalex.org/W3176396223","https://openalex.org/W3213675203"],"related_works":["https://openalex.org/W1544742702","https://openalex.org/W387662165","https://openalex.org/W3004288456","https://openalex.org/W2016355461","https://openalex.org/W1557986679","https://openalex.org/W4362496998","https://openalex.org/W64841805","https://openalex.org/W2184397297","https://openalex.org/W1986386500","https://openalex.org/W2123112337"],"abstract_inverted_index":{"Exploring":[0],"the":[1,26,65,73,144,162],"vast":[2],"amount":[3],"of":[4,28,45,54,78,87],"rapidly":[5],"growing":[6],"scientific":[7,15,18,40,46,60,79,92,115,157,170],"text":[8,19,61,80,171],"data":[9],"is":[10,21],"highly":[11],"beneficial":[12],"for":[13,118,125,169],"real-world":[14,108,136],"discovery.":[16,158],"However,":[17],"mining":[20],"particularly":[22],"challenging":[23],"due":[24],"to":[25],"lack":[27],"specialized":[29],"domain":[30],"knowledge":[31],"in":[32,39],"natural":[33],"language":[34],"context,":[35],"complex":[36],"sentence":[37],"structures":[38],"writing,":[41],"and":[42,57,67,75,102,121,139,149,151,166],"multi-modal":[43],"representations":[44],"knowledge.":[47],"This":[48],"tutorial":[49,132],"presents":[50],"a":[51,85],"comprehensive":[52],"overview":[53],"recent":[55],"research":[56,164],"development":[58],"on":[59,64,135],"mining,":[62],"focusing":[63],"biomedical":[66],"chemistry":[68,141],"domains.":[69],"First,":[70],"we":[71,83,129],"introduce":[72,107],"motivation":[74],"unique":[76],"challenges":[77],"mining.":[81,172],"Then":[82],"discuss":[84,161],"set":[86],"methods":[88],"that":[89],"perform":[90],"effective":[91],"information":[93,145],"extraction,":[94,101],"such":[95,110],"as":[96,111],"named":[97],"entity":[98],"recognition,":[99],"relation":[100],"event":[103],"extraction.":[104],"We":[105,159],"also":[106,160],"applications":[109],"textual":[112],"evidence":[113],"retrieval,":[114],"topic":[116],"contrasting":[117],"drug":[119],"discovery,":[120],"molecule":[122],"representation":[123],"learning":[124],"reaction":[126],"prediction.":[127],"Finally,":[128],"conclude":[130],"our":[131],"by":[133],"demonstrating,":[134],"datasets":[137],"(COVID-19":[138],"organic":[140],"literature),":[142],"how":[143,152],"can":[146,154],"be":[147],"extracted":[148],"retrieved,":[150],"they":[153],"assist":[155],"further":[156],"emerging":[163],"problems":[165],"future":[167],"directions":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}