{"id":"https://openalex.org/W2049334895","doi":"https://doi.org/10.1145/2513549.2514739","title":"Big data opportunities and challenges for IR, text mining and NLP","display_name":"Big data opportunities and challenges for IR, text mining and NLP","publication_year":2013,"publication_date":"2013-10-28","ids":{"openalex":"https://openalex.org/W2049334895","doi":"https://doi.org/10.1145/2513549.2514739","mag":"2049334895"},"language":"en","primary_location":{"id":"doi:10.1145/2513549.2514739","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2513549.2514739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 international workshop on Mining unstructured big data using natural language processing","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/A5060672408","display_name":"Beth Plale","orcid":"https://orcid.org/0000-0003-2164-8132"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Beth Plale","raw_affiliation_strings":["Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5060672408"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":3.2358,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.92878786,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.8504999876022339,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.8504999876022339,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.805412769317627},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7462574243545532},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6662832498550415},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.645577609539032},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.6168823838233948},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5849159359931946},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5381947159767151},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5371782183647156},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5350948572158813},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4694000780582428},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.45763280987739563},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45585545897483826},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.4389655590057373},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.43348559737205505},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.4124048948287964},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38627928495407104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3620142936706543},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.20784741640090942}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.805412769317627},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7462574243545532},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6662832498550415},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.645577609539032},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.6168823838233948},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5849159359931946},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5381947159767151},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5371782183647156},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5350948572158813},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4694000780582428},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.45763280987739563},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45585545897483826},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.4389655590057373},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.43348559737205505},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.4124048948287964},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38627928495407104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3620142936706543},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20784741640090942},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2513549.2514739","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2513549.2514739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 international workshop on Mining unstructured big data using natural language processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W3092506759","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W120741642","https://openalex.org/W138569904","https://openalex.org/W2390914021","https://openalex.org/W2389417819"],"abstract_inverted_index":{"Big":[0],"Data":[1,90,114],"poses":[2,71],"challenges":[3,32],"for":[4,39,99],"text":[5,66],"analysis":[6,41,78],"and":[7,18,36,42,46,57,132],"natural":[8],"language":[9],"processing":[10],"due":[11,108],"to":[12,52,74,80,109],"its":[13],"characteristics":[14],"of":[15,20,28,30,59,86,111,118,120],"volume,":[16],"veracity,":[17],"velocity":[19,115],"the":[21,60,64,87,121,127],"data.":[22],"The":[23],"sheer":[24],"volume":[25],"in":[26,63,92],"terms":[27],"numbers":[29],"documents":[31],"traditional":[33],"local":[34],"repository":[35],"index":[37],"systems":[38],"large-scale":[40],"mining.":[43],"Computation,":[44],"storage":[45],"data":[47,102,104,122],"representation":[48],"must":[49],"work":[50],"together":[51],"provide":[53],"rapid":[54],"access,":[55,76],"search,":[56],"mining":[58],"deep":[61],"knowledge":[62],"large":[65],"collection.":[67],"Text":[68],"under":[69],"copyright":[70],"additional":[72],"barriers":[73],"computational":[75],"where":[77],"has":[79],"be":[81,126],"separated":[82],"from":[83],"human":[84],"consumption":[85],"original":[88,112],"text.":[89],"preprocessing,":[91],"most":[93],"cases,":[94],"remains":[95],"a":[96],"daunting":[97],"task":[98],"big":[100],"textual":[101],"particularly":[103],"veracity":[105],"is":[106,116],"questionable":[107],"age":[110],"materials.":[113],"rate":[117,128],"change":[119],"but":[123],"can":[124],"also":[125],"at":[129],"which":[130],"changes":[131],"corrections":[133],"are":[134],"made.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}