{"id":"https://openalex.org/W2584558077","doi":"https://doi.org/10.1109/bigdata.2016.7840582","title":"On the power of big data: Mining structures from massive, unstructured text data","display_name":"On the power of big data: Mining structures from massive, unstructured text data","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2584558077","doi":"https://doi.org/10.1109/bigdata.2016.7840582","mag":"2584558077"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2016.7840582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","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/A5103750286","display_name":"Jiawei Han","orcid":null},"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":"Jiawei Han","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, USA","University of Illinois at Urbana-Champaign, Urbana, IL, US"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, US","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5103750286"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":1.2854,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.87832804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9735000133514404,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9735000133514404,"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":0.968500018119812,"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":0.9532999992370605,"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":0.7971900701522827},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.719447910785675},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5869654417037964},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5817398428916931},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.5294625163078308},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4866560101509094},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.41136255860328674},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.38981348276138306},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3355504870414734},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.317440927028656},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25126445293426514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7971900701522827},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.719447910785675},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5869654417037964},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5817398428916931},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.5294625163078308},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4866560101509094},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.41136255860328674},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38981348276138306},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3355504870414734},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.317440927028656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25126445293426514},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2016.7840582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2468296273","https://openalex.org/W3157828377","https://openalex.org/W2604454537","https://openalex.org/W2019158987","https://openalex.org/W4377992839","https://openalex.org/W2883748392","https://openalex.org/W2808284704","https://openalex.org/W2897702399","https://openalex.org/W4206028705","https://openalex.org/W2757431232"],"abstract_inverted_index":{"Summary":[0],"form":[1,15],"only":[2,52],"given.":[3],"The":[4],"real-world":[5],"big":[6],"data":[7,31,82,110,141],"are":[8],"largely":[9],"unstructured,":[10],"interconnected,":[11],"and":[12,35,40,86,116,121,145],"in":[13],"the":[14,22],"of":[16,21],"natural":[17],"language":[18],"text.":[19],"One":[20],"grand":[23],"challenges":[24],"is":[25],"to":[26,37,124],"turn":[27,109],"such":[28,71,119,130],"massive":[29,61,72,80,139],"unstructured":[30],"into":[32,111,142],"structured":[33,38,113,143],"ones,":[34],"then":[36,117],"networks":[39,123,144],"actionable":[41],"knowledge.":[42,127,147],"We":[43,63,128],"propose":[44,100],"a":[45,101,131,134],"data-intensive":[46],"text":[47,73,81,140],"mining":[48],"approach":[49],"that":[50,106],"requires":[51],"distant":[53,84],"supervision":[54,57],"or":[55],"minimal":[56],"but":[58],"relies":[59],"on":[60],"data.":[62],"show":[64,129],"quality":[65],"phrases":[66],"can":[67,76,90],"be":[68,77,91],"mined":[69],"from":[70,79],"data,":[74],"types":[75],"extracted":[78],"with":[83],"supervision,":[85],"relationships":[87],"among":[88],"entities":[89],"discovered":[92],"by":[93],"meta-path":[94],"guided":[95],"network":[96],"embedding.":[97],"Finally,":[98],"we":[99],"D2N2K":[102],"(i.e.,":[103],"data-to-network-to-knowledge)":[104],"paradigm,":[105],"is,":[107],"first":[108],"relatively":[112],"information":[114],"networks,":[115],"mine":[118],"text-rich":[120],"structure-rich":[122],"generate":[125],"useful":[126,146],"paradigm":[132],"represents":[133],"promising":[135],"direction":[136],"at":[137],"turning":[138]},"counts_by_year":[{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}