{"id":"https://openalex.org/W4400352977","doi":"https://doi.org/10.1186/s40537-024-00948-z","title":"Exploring AI-driven approaches for unstructured document analysis and future horizons","display_name":"Exploring AI-driven approaches for unstructured document analysis and future horizons","publication_year":2024,"publication_date":"2024-07-05","ids":{"openalex":"https://openalex.org/W4400352977","doi":"https://doi.org/10.1186/s40537-024-00948-z"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-024-00948-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-024-00948-z","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-024-00948-z","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-024-00948-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041221611","display_name":"Supriya V. Mahadevkar","orcid":null},"institutions":[{"id":"https://openalex.org/I244572783","display_name":"Symbiosis International University","ror":"https://ror.org/005r2ww51","country_code":"IN","type":"education","lineage":["https://openalex.org/I244572783"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Supriya V. Mahadevkar","raw_affiliation_strings":["Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, 412115, India"],"affiliations":[{"raw_affiliation_string":"Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, 412115, India","institution_ids":["https://openalex.org/I244572783"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025236262","display_name":"Shruti Patil","orcid":"https://orcid.org/0000-0002-4903-1540"},"institutions":[{"id":"https://openalex.org/I244572783","display_name":"Symbiosis International University","ror":"https://ror.org/005r2ww51","country_code":"IN","type":"education","lineage":["https://openalex.org/I244572783"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shruti Patil","raw_affiliation_strings":["Symbiosis Centre for Applied Artificial Intelligence, Symbiosis Institute of Technology Symbiosis International (Deemed University), Pune, 412115, India"],"affiliations":[{"raw_affiliation_string":"Symbiosis Centre for Applied Artificial Intelligence, Symbiosis Institute of Technology Symbiosis International (Deemed University), Pune, 412115, India","institution_ids":["https://openalex.org/I244572783"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077770842","display_name":"Ketan Kotecha","orcid":"https://orcid.org/0000-0003-2653-3780"},"institutions":[{"id":"https://openalex.org/I244572783","display_name":"Symbiosis International University","ror":"https://ror.org/005r2ww51","country_code":"IN","type":"education","lineage":["https://openalex.org/I244572783"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ketan Kotecha","raw_affiliation_strings":["Symbiosis Centre for Applied Artificial Intelligence, Symbiosis Institute of Technology Symbiosis International (Deemed University), Pune, 412115, India"],"affiliations":[{"raw_affiliation_string":"Symbiosis Centre for Applied Artificial Intelligence, Symbiosis Institute of Technology Symbiosis International (Deemed University), Pune, 412115, India","institution_ids":["https://openalex.org/I244572783"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100022729","display_name":"Lim Way Soong","orcid":null},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Lim Way Soong","raw_affiliation_strings":["Faculty of Engineering and Technology, Multimedia University, Cyberjaya, Malaysia"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Technology, Multimedia University, Cyberjaya, Malaysia","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021051196","display_name":"Tanupriya Choudhury","orcid":"https://orcid.org/0000-0002-9826-2759"},"institutions":[{"id":"https://openalex.org/I244572783","display_name":"Symbiosis International University","ror":"https://ror.org/005r2ww51","country_code":"IN","type":"education","lineage":["https://openalex.org/I244572783"]},{"id":"https://openalex.org/I5847235","display_name":"University of Petroleum and Energy Studies","ror":"https://ror.org/04q2jes40","country_code":"IN","type":"education","lineage":["https://openalex.org/I5847235"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tanupriya Choudhury","raw_affiliation_strings":["CSE Department, Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, Maharashtra, 412115, India","School of Computer Science, University of Petroleum and Energy Studies (UPES), Dehradun, Uttarakhand, 248002, India"],"affiliations":[{"raw_affiliation_string":"CSE Department, Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, Maharashtra, 412115, India","institution_ids":["https://openalex.org/I244572783"]},{"raw_affiliation_string":"School of Computer Science, University of Petroleum and Energy Studies (UPES), Dehradun, Uttarakhand, 248002, India","institution_ids":["https://openalex.org/I5847235"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100022729"],"corresponding_institution_ids":["https://openalex.org/I173029219"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":21.204,"has_fulltext":true,"cited_by_count":60,"citation_normalized_percentile":{"value":0.99568391,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"11","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9940000176429749,"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/T10028","display_name":"Topic Modeling","score":0.9940000176429749,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9872000217437744,"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":0.8119158744812012},{"id":"https://openalex.org/keywords/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.8081782460212708},{"id":"https://openalex.org/keywords/new-horizons","display_name":"New horizons","score":0.5864939093589783},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.5366866588592529},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4776533842086792},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3797781765460968},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3339281678199768},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.25761187076568604},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.21788161993026733},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.16824373602867126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8119158744812012},{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.8081782460212708},{"id":"https://openalex.org/C2992257854","wikidata":"https://www.wikidata.org/wiki/Q48461","display_name":"New horizons","level":3,"score":0.5864939093589783},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.5366866588592529},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4776533842086792},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3797781765460968},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3339281678199768},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.25761187076568604},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.21788161993026733},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.16824373602867126},{"id":"https://openalex.org/C29829512","wikidata":"https://www.wikidata.org/wiki/Q40218","display_name":"Spacecraft","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/s40537-024-00948-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-024-00948-z","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-024-00948-z","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:shdl.mmu.edu.my:12699","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196753","display_name":"Siti Hasmah Digital Library-MMU Institutiona Repository (Multimedia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173029219","host_organization_name":"Multimedia University","host_organization_lineage":["https://openalex.org/I173029219"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"NonPeerReviewed"},{"id":"pmh:oai:doaj.org/article:0d4c356a3cd8474cb6766b0091ac80b2","is_oa":true,"landing_page_url":"https://doaj.org/article/0d4c356a3cd8474cb6766b0091ac80b2","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Big Data, Vol 11, Iss 1, Pp 1-54 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s40537-024-00948-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-024-00948-z","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-024-00948-z","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320313202","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400352977.pdf","grobid_xml":"https://content.openalex.org/works/W4400352977.grobid-xml"},"referenced_works_count":95,"referenced_works":["https://openalex.org/W791527587","https://openalex.org/W2002661695","https://openalex.org/W2065632200","https://openalex.org/W2072498467","https://openalex.org/W2093526417","https://openalex.org/W2094070378","https://openalex.org/W2099534604","https://openalex.org/W2137472923","https://openalex.org/W2152928267","https://openalex.org/W2160511393","https://openalex.org/W2219661736","https://openalex.org/W2342299174","https://openalex.org/W2516822814","https://openalex.org/W2526903591","https://openalex.org/W2537675719","https://openalex.org/W2554500017","https://openalex.org/W2615884691","https://openalex.org/W2734358244","https://openalex.org/W2752571292","https://openalex.org/W2768488789","https://openalex.org/W2768950517","https://openalex.org/W2779545291","https://openalex.org/W2782040381","https://openalex.org/W2789244308","https://openalex.org/W2790618693","https://openalex.org/W2806031239","https://openalex.org/W2883558401","https://openalex.org/W2888746867","https://openalex.org/W2893960629","https://openalex.org/W2901170937","https://openalex.org/W2912576923","https://openalex.org/W2916349291","https://openalex.org/W2919466488","https://openalex.org/W2920124529","https://openalex.org/W2934353002","https://openalex.org/W2946108305","https://openalex.org/W2956037940","https://openalex.org/W2963687456","https://openalex.org/W2964000578","https://openalex.org/W2964536243","https://openalex.org/W2965009206","https://openalex.org/W2969385558","https://openalex.org/W2971987430","https://openalex.org/W2973047034","https://openalex.org/W2973803552","https://openalex.org/W2980121369","https://openalex.org/W2981089724","https://openalex.org/W2982358276","https://openalex.org/W2988423567","https://openalex.org/W2991918928","https://openalex.org/W2994804941","https://openalex.org/W2995151999","https://openalex.org/W2996441822","https://openalex.org/W2997154779","https://openalex.org/W2998301900","https://openalex.org/W3003484198","https://openalex.org/W3006008097","https://openalex.org/W3006227201","https://openalex.org/W3013327809","https://openalex.org/W3024724345","https://openalex.org/W3037641445","https://openalex.org/W3043249783","https://openalex.org/W3045882047","https://openalex.org/W3080359515","https://openalex.org/W3089446975","https://openalex.org/W3099750501","https://openalex.org/W3099847344","https://openalex.org/W3100423079","https://openalex.org/W3104953317","https://openalex.org/W3106784868","https://openalex.org/W3122950209","https://openalex.org/W3125832420","https://openalex.org/W3137109085","https://openalex.org/W3138912197","https://openalex.org/W3153334746","https://openalex.org/W3155464240","https://openalex.org/W3168508953","https://openalex.org/W3180901325","https://openalex.org/W3185020631","https://openalex.org/W3215259583","https://openalex.org/W4221047533","https://openalex.org/W4221151164","https://openalex.org/W4223415467","https://openalex.org/W4225650808","https://openalex.org/W4226020328","https://openalex.org/W4281621698","https://openalex.org/W4283710510","https://openalex.org/W4297094728","https://openalex.org/W4303833072","https://openalex.org/W4306152189","https://openalex.org/W4308335753","https://openalex.org/W4320728842","https://openalex.org/W4390873338","https://openalex.org/W6725960765","https://openalex.org/W6840287690"],"related_works":["https://openalex.org/W2389401371","https://openalex.org/W2218797720","https://openalex.org/W4295797343","https://openalex.org/W2413102523","https://openalex.org/W2981089724","https://openalex.org/W2261525379","https://openalex.org/W2805468299","https://openalex.org/W2889935511","https://openalex.org/W3143721902","https://openalex.org/W4231652189"],"abstract_inverted_index":{"Abstract":[0],"In":[1],"the":[2,14,34,78,100,144,230,241],"current":[3],"industrial":[4],"landscape,":[5],"a":[6,58,71,207,217],"significant":[7],"number":[8],"of":[9,74,80,102,232],"sectors":[10],"are":[11,151],"grappling":[12],"with":[13,127,202,245],"challenges":[15,243],"posed":[16],"by":[17,52],"unstructured":[18,83,103,189,225,246],"data,":[19],"which":[20],"incurs":[21],"financial":[22],"losses":[23],"amounting":[24],"to":[25,36,90,143,239],"millions":[26],"annually.":[27],"If":[28],"harnessed":[29],"effectively,":[30],"this":[31,213],"data":[32,247],"has":[33,108],"potential":[35],"substantially":[37],"boost":[38],"operational":[39],"efficiency.":[40],"Traditional":[41],"methods":[42,114],"for":[43,77,153,162,220],"extracting":[44,185],"information":[45,81,105,186,222],"have":[46],"their":[47],"limitations;":[48],"however,":[49,199],"solutions":[50],"powered":[51],"artificial":[53],"intelligence":[54],"(AI)":[55],"could":[56],"provide":[57],"more":[59],"fitting":[60],"alternative.":[61],"There":[62],"is":[63],"an":[64,159],"evident":[65],"gap":[66],"in":[67,133,172,183],"scholarly":[68],"research":[69,97],"concerning":[70],"comprehensive":[72],"evaluation":[73],"AI-driven":[75],"techniques":[76,180],"extraction":[79,113,223],"from":[82,147,187,224],"content.":[84],"This":[85,157],"systematic":[86],"literature":[87],"review":[88,176,214],"aims":[89],"identify,":[91],"assess,":[92],"and":[93,150,194,237],"deliberate":[94],"on":[95,117],"prospective":[96],"directions":[98],"within":[99],"field":[101],"document":[104,129,204],"extraction.":[106],"It":[107],"been":[109],"observed":[110],"that":[111,166,178],"prevailing":[112],"primarily":[115],"depend":[116],"static":[118],"patterns":[119],"or":[120],"rules,":[121],"often":[122],"proving":[123],"inadequate":[124],"when":[125,200],"faced":[126],"complex":[128,169],"structures":[130],"typically":[131],"encountered":[132,171],"real-world":[134],"scenarios,":[135],"such":[136],"as":[137],"medical":[138],"records.":[139],"Datasets":[140],"currently":[141],"available":[142],"public":[145],"suffer":[146],"low":[148],"quality":[149],"tailored":[152],"specific":[154],"tasks":[155],"only.":[156],"underscores":[158],"urgent":[160],"need":[161],"developing":[163],"new":[164],"datasets":[165],"accurately":[167],"reflect":[168],"issues":[170],"practical":[173],"settings.":[174],"The":[175],"reveals":[177],"AI-based":[179,211],"show":[181],"promise":[182],"autonomously":[184],"diverse":[188,242],"documents,":[190],"encompassing":[191],"both":[192],"printed":[193],"handwritten":[195],"text.":[196],"Challenges":[197],"arise,":[198],"dealing":[201],"varied":[203],"layouts.":[205],"Proposing":[206],"framework":[208],"through":[209],"hybrid":[210],"approaches,":[212],"envisions":[215],"processing":[216],"high-quality":[218],"dataset":[219],"automatic":[221],"documents.":[226],"Additionally,":[227],"it":[228],"emphasizes":[229],"importance":[231],"collaborative":[233],"efforts":[234],"between":[235],"organizations":[236],"researchers":[238],"address":[240],"associated":[244],"analysis.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":48},{"year":2024,"cited_by_count":4}],"updated_date":"2026-03-23T07:41:27.035349","created_date":"2025-10-10T00:00:00"}
