{"id":"https://openalex.org/W2810598897","doi":"https://doi.org/10.1109/codit.2018.8394841","title":"Learning statistics from raw text documents","display_name":"Learning statistics from raw text documents","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2810598897","doi":"https://doi.org/10.1109/codit.2018.8394841","mag":"2810598897"},"language":"en","primary_location":{"id":"doi:10.1109/codit.2018.8394841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codit.2018.8394841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 5th International Conference on Control, Decision and Information Technologies (CoDIT)","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/A5081000081","display_name":"Nour El Houda Ben Chaabene","orcid":"https://orcid.org/0000-0003-1949-9596"},"institutions":[{"id":"https://openalex.org/I83259278","display_name":"Manouba University","ror":"https://ror.org/0503ejf32","country_code":"TN","type":"education","lineage":["https://openalex.org/I83259278"]}],"countries":["TN"],"is_corresponding":true,"raw_author_name":"Nour El Houda Ben Chaabene","raw_affiliation_strings":["RIADI Laboratory, University of Manouba, Manouba, Tunisia"],"affiliations":[{"raw_affiliation_string":"RIADI Laboratory, University of Manouba, Manouba, Tunisia","institution_ids":["https://openalex.org/I83259278"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023719710","display_name":"Maha Mallek","orcid":null},"institutions":[{"id":"https://openalex.org/I83259278","display_name":"Manouba University","ror":"https://ror.org/0503ejf32","country_code":"TN","type":"education","lineage":["https://openalex.org/I83259278"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Maha Mallek","raw_affiliation_strings":["COSMOS Laboratory, University of Manouba, Manouba, Tunisia"],"affiliations":[{"raw_affiliation_string":"COSMOS Laboratory, University of Manouba, Manouba, Tunisia","institution_ids":["https://openalex.org/I83259278"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081000081"],"corresponding_institution_ids":["https://openalex.org/I83259278"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06694145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"321","last_page":"326"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9958000183105469,"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":0.9958000183105469,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9927999973297119,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9912999868392944,"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":0.7570500373840332},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.6004391312599182},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5790175795555115},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5584502220153809},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5502316355705261},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5453450679779053},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.47081905603408813},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.44661185145378113},{"id":"https://openalex.org/keywords/statistical-analysis","display_name":"Statistical analysis","score":0.41586410999298096},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40416452288627625},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3261936902999878},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.18965619802474976},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08886763453483582}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7570500373840332},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.6004391312599182},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5790175795555115},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5584502220153809},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5502316355705261},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5453450679779053},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.47081905603408813},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.44661185145378113},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.41586410999298096},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40416452288627625},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3261936902999878},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.18965619802474976},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08886763453483582},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/codit.2018.8394841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codit.2018.8394841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 5th International Conference on Control, Decision and Information Technologies (CoDIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1484962238","https://openalex.org/W1489949474","https://openalex.org/W1564518192","https://openalex.org/W1775605004","https://openalex.org/W2005422315","https://openalex.org/W2068737686","https://openalex.org/W2069140227","https://openalex.org/W2120814856","https://openalex.org/W2135813353","https://openalex.org/W2148540243","https://openalex.org/W2163362093"],"related_works":["https://openalex.org/W3157828377","https://openalex.org/W2468296273","https://openalex.org/W4377992839","https://openalex.org/W2937168573","https://openalex.org/W2261525379","https://openalex.org/W2805468299","https://openalex.org/W4241804824","https://openalex.org/W4231652189","https://openalex.org/W2608358066","https://openalex.org/W4388251808"],"abstract_inverted_index":{"Statistics":[0],"are":[1,146],"still":[2],"the":[3,33,46,62,69,83,94,105,109,116,140,151],"best":[4],"tool":[5],"for":[6,59,129],"analyzing":[7],"political,":[8],"economic":[9],"and":[10,19,32,99,108],"social":[11],"phenomena.":[12],"Among":[13],"other":[14],"things,":[15],"they":[16],"allow":[17],"projections":[18],"forecasts":[20],"to":[21,24,41,78,92,111,120,136,148],"be":[22],"used":[23],"assist":[25],"in":[26,124,134,139],"decision-making.":[27],"The":[28],"today's":[29],"information":[30],"society,":[31],"era":[34],"of":[35,45,71,85,104,115,142,153],"\u201cBig":[36],"Data\u201d,":[37],"have":[38],"facilitated":[39],"access":[40],"information.":[42],"However,":[43],"most":[44],"available":[47,58],"data":[48,133,144],"is":[49,55,77,90],"unstructured":[50],"and,":[51],"as":[52],"a":[53,72,86,112],"result,":[54],"not":[56],"readily":[57],"use":[60],"by":[61],"IT":[63],"tool,":[64],"particularly":[65],"statistical":[66,80,95,132],"data.":[67],"In":[68],"context":[70],"research":[73],"project":[74],"whose":[75],"objective":[76],"extract":[79],"in-formation":[81],"from":[82],"results":[84],"Web":[87],"search,":[88],"it":[89],"imperative":[91],"recognize":[93],"variables":[96],"dealt":[97],"with":[98,150],"their":[100],"values":[101],"associated.":[102],"One":[103],"primordial":[106],"stages":[107],"assignment,":[110],"given":[113],"variable,":[114],"different":[117],"instances":[118],"corresponding":[119],"it.":[121],"We":[122],"propose":[123],"this":[125],"work":[126],"an":[127],"approach":[128],"identifying":[130],"these":[131],"order":[135],"represent":[137],"them":[138],"form":[141],"structured":[143],"that":[145],"easy":[147],"process":[149],"help":[152],"computers.":[154]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
