{"id":"https://openalex.org/W3174123549","doi":"https://doi.org/10.1109/access.2021.3089924","title":"An Incremental Approach to Corpus Design and Construction: Application to a Large Contemporary Saudi Corpus","display_name":"An Incremental Approach to Corpus Design and Construction: Application to a Large Contemporary Saudi Corpus","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3174123549","doi":"https://doi.org/10.1109/access.2021.3089924","mag":"3174123549"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3089924","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3089924","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09458313.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09458313.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041905983","display_name":"Hebah ElGibreen","orcid":null},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Hebah Elgibreen","raw_affiliation_strings":["Center of Smart Robotics Research, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-3764-6169","affiliations":[{"raw_affiliation_string":"Center of Smart Robotics Research, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]},{"raw_affiliation_string":"College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043253462","display_name":"Mohammed Faisal","orcid":"https://orcid.org/0000-0001-7720-0076"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Mohammed Faisal","raw_affiliation_strings":["Center of Smart Robotics Research, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","College of Applied Computer Sciences, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0001-7720-0076","affiliations":[{"raw_affiliation_string":"Center of Smart Robotics Research, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]},{"raw_affiliation_string":"College of Applied Computer Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108447036","display_name":"Mansour Al Sulaiman","orcid":null},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Mansour Al Sulaiman","raw_affiliation_strings":["Center of Smart Robotics Research, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0003-2866-184X","affiliations":[{"raw_affiliation_string":"Center of Smart Robotics Research, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]},{"raw_affiliation_string":"College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048958429","display_name":"Sherif Abdou","orcid":"https://orcid.org/0000-0002-8338-856X"},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Sherif Abdou","raw_affiliation_strings":["Faculty of Computers and Artificial Intelligence, Cairo University, Giza, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computers and Artificial Intelligence, Cairo University, Giza, Egypt","institution_ids":["https://openalex.org/I145487455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047566160","display_name":"Mohamed Amine Mekhtiche","orcid":"https://orcid.org/0000-0001-9478-9206"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Mohamed Amine Mekhtiche","raw_affiliation_strings":["Center of Smart Robotics Research, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0001-9478-9206","affiliations":[{"raw_affiliation_string":"Center of Smart Robotics Research, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]},{"raw_affiliation_string":"College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023524652","display_name":"Abdullah M. Moussa","orcid":"https://orcid.org/0000-0001-7556-9267"},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Abdullah M. Moussa","raw_affiliation_strings":["Faculty of Computers and Artificial Intelligence, Cairo University, Giza, Egypt"],"raw_orcid":"https://orcid.org/0000-0001-7556-9267","affiliations":[{"raw_affiliation_string":"Faculty of Computers and Artificial Intelligence, Cairo University, Giza, Egypt","institution_ids":["https://openalex.org/I145487455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086569517","display_name":"Yousef Al-Ohali","orcid":"https://orcid.org/0000-0002-4228-7199"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Yousef A. Alohali","raw_affiliation_strings":["Center of Smart Robotics Research, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Smart Robotics Research, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]},{"raw_affiliation_string":"College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083084430","display_name":"Wadood Abdul","orcid":"https://orcid.org/0000-0002-6871-6633"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Wadood Abdul","raw_affiliation_strings":["Center of Smart Robotics Research, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Smart Robotics Research, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]},{"raw_affiliation_string":"College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080711681","display_name":"Ghulam Muhammad","orcid":"https://orcid.org/0000-0002-9781-3969"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Ghulam Muhammad","raw_affiliation_strings":["Center of Smart Robotics Research, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-9781-3969","affiliations":[{"raw_affiliation_string":"Center of Smart Robotics Research, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]},{"raw_affiliation_string":"College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030016694","display_name":"Mohsen Rashwan","orcid":"https://orcid.org/0000-0003-3712-5408"},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Mohsen Rashwan","raw_affiliation_strings":["Faculty of Engineering, Cairo University, Giza, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Cairo University, Giza, Egypt","institution_ids":["https://openalex.org/I145487455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081962715","display_name":"Mohammed Algabri","orcid":"https://orcid.org/0000-0001-7962-8121"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Mohammed Algabri","raw_affiliation_strings":["Center of Smart Robotics Research, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0001-7962-8121","affiliations":[{"raw_affiliation_string":"Center of Smart Robotics Research, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]},{"raw_affiliation_string":"College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5041905983"],"corresponding_institution_ids":["https://openalex.org/I28022161"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.1199,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82154169,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"9","issue":null,"first_page":"88405","last_page":"88428"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"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":0.9898999929428101,"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":0.8439595699310303},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7082915902137756},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6994669437408447},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6947093605995178},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.587028980255127},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5201140642166138},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.5133439898490906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5084061026573181},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41267716884613037},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.41184180974960327},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1672554612159729},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09247881174087524}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8439595699310303},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7082915902137756},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6994669437408447},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6947093605995178},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.587028980255127},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5201140642166138},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.5133439898490906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5084061026573181},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41267716884613037},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.41184180974960327},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1672554612159729},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09247881174087524},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3089924","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3089924","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09458313.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:82c7253562704e71bcb170607187366d","is_oa":true,"landing_page_url":"https://doaj.org/article/82c7253562704e71bcb170607187366d","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 88405-88428 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3089924","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3089924","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09458313.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321145","display_name":"King Saud University","ror":"https://ror.org/02f81g417"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3174123549.pdf","grobid_xml":"https://content.openalex.org/works/W3174123549.grobid-xml"},"referenced_works_count":69,"referenced_works":["https://openalex.org/W11511616","https://openalex.org/W115020434","https://openalex.org/W131663347","https://openalex.org/W179850243","https://openalex.org/W195406672","https://openalex.org/W630532510","https://openalex.org/W937194849","https://openalex.org/W1226400880","https://openalex.org/W1981685568","https://openalex.org/W1984708705","https://openalex.org/W2100976324","https://openalex.org/W2147272182","https://openalex.org/W2168576900","https://openalex.org/W2235207698","https://openalex.org/W2250816155","https://openalex.org/W2251259636","https://openalex.org/W2251657882","https://openalex.org/W2252033489","https://openalex.org/W2252067490","https://openalex.org/W2252085349","https://openalex.org/W2419539795","https://openalex.org/W2471147443","https://openalex.org/W2562238432","https://openalex.org/W2585345551","https://openalex.org/W2613296002","https://openalex.org/W2625475744","https://openalex.org/W2767299343","https://openalex.org/W2767566483","https://openalex.org/W2770803436","https://openalex.org/W2791757336","https://openalex.org/W2802540964","https://openalex.org/W2805431570","https://openalex.org/W2806962830","https://openalex.org/W2900704097","https://openalex.org/W2907500287","https://openalex.org/W2910925125","https://openalex.org/W2944152053","https://openalex.org/W2945061898","https://openalex.org/W2947502927","https://openalex.org/W2948589047","https://openalex.org/W2963943537","https://openalex.org/W2967690825","https://openalex.org/W2970345257","https://openalex.org/W3012069291","https://openalex.org/W3016055861","https://openalex.org/W3018324503","https://openalex.org/W3022935508","https://openalex.org/W3032746405","https://openalex.org/W3039503982","https://openalex.org/W3118913631","https://openalex.org/W4211260480","https://openalex.org/W4297663785","https://openalex.org/W4300167661","https://openalex.org/W6600454326","https://openalex.org/W6604586875","https://openalex.org/W6605374713","https://openalex.org/W6607331989","https://openalex.org/W6624471508","https://openalex.org/W6628134086","https://openalex.org/W6690218062","https://openalex.org/W6691525129","https://openalex.org/W6717262007","https://openalex.org/W6726719933","https://openalex.org/W6737098610","https://openalex.org/W6751400415","https://openalex.org/W6752073440","https://openalex.org/W6758351866","https://openalex.org/W6778931571","https://openalex.org/W7051469422"],"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":{"Due":[0],"to":[1,26,41,63,121,134,142,184,205,216],"the":[2,8,47,50,64,71,76,97,122,146,164,169,176,190,203,208,223],"rapid":[3],"developments":[4,48],"in":[5,49,110,173,178,221],"technology":[6],"and":[7,99,144,154,161,175,200],"sudden":[9],"expansion":[10],"of":[11,22,46,192,213],"social":[12],"media":[13],"use,":[14],"Dialect":[15],"Arabic":[16,31,37],"has":[17],"become":[18],"an":[19],"important":[20],"source":[21],"data":[23],"that":[24,43,131,138,207],"needs":[25],"be":[27,156,212],"addressed":[28],"when":[29],"building":[30,168],"corpora.":[32],"In":[33],"this":[34,193],"paper,":[35,194],"thirty-three":[36],"corpora":[38,55,68],"are":[39,139,187,198,219],"surveyed":[40],"show":[42],"despite":[44],"all":[45],"literature,":[51],"Saudi":[52,73,80],"dialect":[53],"(SD)":[54],"still":[56],"need":[57],"further":[58],"expansion.":[59],"This":[60,117,149],"paper":[61,118],"contributes":[62,120],"literature":[65,123],"on":[66],"SD":[67,90,101,180],"by":[69,124],"creating":[70],"largest":[72,100],"corpus":[74,102,210,224],"-":[75,83],"King":[77],"Saud":[78],"University":[79],"Corpus":[81],"(KSUSC)":[82],"with":[84,182,202,225,234],"+1B":[85],"total":[86],"words,":[87],"including":[88],"+119M":[89],"words.":[91],"The":[92],"KSUSC":[93,170,204],"not":[94],"only":[95],"is":[96,104,132,152,171],"newest":[98],"but":[103],"also":[105,119],"diverse,":[106],"covering":[107],"26":[108],"domains":[109],"text":[111,181],"collected":[112,147],"from":[113],"five":[114],"different":[115,159,195],"sources.":[116],"developing":[125],"a":[126],"new":[127],"incremental":[128,150],"preprocessing":[129],"system":[130,151],"used":[133,141,201],"create":[135],"relevant":[136],"lexicons":[137,233],"then":[140],"clean":[143],"normalize":[145],"data.":[148],"scalable":[153],"can":[155,211],"adapted":[157],"for":[158,167],"resources":[160],"dialects.":[162],"Moreover,":[163],"collection":[165],"process":[166],"discussed":[172],"detail,":[174],"challenges":[177],"collecting":[179],"respect":[183],"each":[185],"platform":[186],"highlighted.":[188],"By":[189],"end":[191],"design":[196],"criteria":[197],"proposed":[199],"conclude":[206],"resulting":[209,232],"great":[214],"benefit":[215],"researchers":[217],"who":[218],"interested":[220],"integrating":[222],"their":[226],"own":[227],"work":[228],"or":[229],"using":[230],"its":[231],"Saudi-based":[235],"NLP":[236],"tasks.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
