{"id":"https://openalex.org/W4388666591","doi":"https://doi.org/10.1109/access.2023.3332710","title":"An Analytical Analysis of Text Stemming Methodologies in Information Retrieval and Natural Language Processing Systems","display_name":"An Analytical Analysis of Text Stemming Methodologies in Information Retrieval and Natural Language Processing Systems","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4388666591","doi":"https://doi.org/10.1109/access.2023.3332710"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3332710","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3332710","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10318122.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":null,"license_id":null,"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/ielx7/6287639/6514899/10318122.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048393358","display_name":"Abdul Jabbar","orcid":"https://orcid.org/0000-0001-8657-1282"},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Abdul Jabbar","raw_affiliation_strings":["Department of Computer Science, COMSATS University Islamabad (CUI), Main Campus, Tarlai Kalan, Islamabad, Pakistan","Department of Computer Science, COMSATS University Islamabad (CUI), Main Campus, Park Road, Tarlai Kalan, Islamabad, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, COMSATS University Islamabad (CUI), Main Campus, Tarlai Kalan, Islamabad, Pakistan","institution_ids":["https://openalex.org/I16076960"]},{"raw_affiliation_string":"Department of Computer Science, COMSATS University Islamabad (CUI), Main Campus, Park Road, Tarlai Kalan, Islamabad, Pakistan","institution_ids":["https://openalex.org/I16076960"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072097752","display_name":"Sajid Iqbal","orcid":"https://orcid.org/0000-0002-8464-2275"},"institutions":[{"id":"https://openalex.org/I4626487","display_name":"King Faisal University","ror":"https://ror.org/00dn43547","country_code":"SA","type":"education","lineage":["https://openalex.org/I4626487"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Sajid Iqbal","raw_affiliation_strings":["Department of Information Systems, College of Computer Science and Information Technology, King Faisal University, Al Hofuf, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, College of Computer Science and Information Technology, King Faisal University, Al Hofuf, Saudi Arabia","institution_ids":["https://openalex.org/I4626487"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Manzoor Ilahi Tamimy","orcid":"https://orcid.org/0000-0003-0093-6186"},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Manzoor Ilahi Tamimy","raw_affiliation_strings":["Department of Computer Science, COMSATS University Islamabad (CUI), Main Campus, Tarlai Kalan, Islamabad, Pakistan","Department of Computer Science, COMSATS University Islamabad (CUI), Main Campus, Park Road, Tarlai Kalan, Islamabad, Pakistan"],"raw_orcid":"https://orcid.org/0000-0003-0093-6186","affiliations":[{"raw_affiliation_string":"Department of Computer Science, COMSATS University Islamabad (CUI), Main Campus, Tarlai Kalan, Islamabad, Pakistan","institution_ids":["https://openalex.org/I16076960"]},{"raw_affiliation_string":"Department of Computer Science, COMSATS University Islamabad (CUI), Main Campus, Park Road, Tarlai Kalan, Islamabad, Pakistan","institution_ids":["https://openalex.org/I16076960"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062125413","display_name":"Amjad Rehman","orcid":"https://orcid.org/0000-0002-3817-2655"},"institutions":[{"id":"https://openalex.org/I142024983","display_name":"Prince Sultan University","ror":"https://ror.org/053mqrf26","country_code":"SA","type":"education","lineage":["https://openalex.org/I142024983"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Amjad Rehman","raw_affiliation_strings":["Artificial Intelligence & Data Analytics Laboratory (AIDA), CCIS, Prince Sultan University, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-3817-2655","affiliations":[{"raw_affiliation_string":"Artificial Intelligence & Data Analytics Laboratory (AIDA), CCIS, Prince Sultan University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I142024983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077942586","display_name":"Saeed Ali Bahaj","orcid":"https://orcid.org/0000-0003-3406-4320"},"institutions":[{"id":"https://openalex.org/I142608572","display_name":"Prince Sattam Bin Abdulaziz University","ror":"https://ror.org/04jt46d36","country_code":"SA","type":"education","lineage":["https://openalex.org/I142608572"]},{"id":"https://openalex.org/I319841309","display_name":"Hadhramout University","ror":"https://ror.org/02kv0px94","country_code":"YE","type":"education","lineage":["https://openalex.org/I319841309"]},{"id":"https://openalex.org/I4210165529","display_name":"University of Business and Technology","ror":"https://ror.org/05tcr1n44","country_code":"SA","type":"education","lineage":["https://openalex.org/I4210165529"]}],"countries":["SA","YE"],"is_corresponding":false,"raw_author_name":"Saeed Ali Bahaj","raw_affiliation_strings":["MIS Department, College of Business Administration, Prince Sattam bin Abdulaziz University, Al-Kharj, Saudi Arabia","Department of Computer Engineering, College of Engineering and Petroleum, Hadhramaut University, Mukalla, Hadhramout, Yemen"],"raw_orcid":"https://orcid.org/0000-0003-3406-4320","affiliations":[{"raw_affiliation_string":"MIS Department, College of Business Administration, Prince Sattam bin Abdulaziz University, Al-Kharj, Saudi Arabia","institution_ids":["https://openalex.org/I142608572","https://openalex.org/I4210165529"]},{"raw_affiliation_string":"Department of Computer Engineering, College of Engineering and Petroleum, Hadhramaut University, Mukalla, Hadhramout, Yemen","institution_ids":["https://openalex.org/I319841309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018549351","display_name":"Tanzila Saba","orcid":"https://orcid.org/0000-0003-3138-3801"},"institutions":[{"id":"https://openalex.org/I142024983","display_name":"Prince Sultan University","ror":"https://ror.org/053mqrf26","country_code":"SA","type":"education","lineage":["https://openalex.org/I142024983"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Tanzila Saba","raw_affiliation_strings":["Artificial Intelligence & Data Analytics Laboratory (AIDA), CCIS, Prince Sultan University, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0003-3138-3801","affiliations":[{"raw_affiliation_string":"Artificial Intelligence & Data Analytics Laboratory (AIDA), CCIS, Prince Sultan University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I142024983"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5048393358"],"corresponding_institution_ids":["https://openalex.org/I16076960"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":5.753,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.96930072,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"11","issue":null,"first_page":"133681","last_page":"133702"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9944000244140625,"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":0.9944000244140625,"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":0.9911999702453613,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9861000180244446,"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":0.8165500164031982},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5868290066719055},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5707131624221802},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5295206904411316},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4935673475265503},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.4536516070365906},{"id":"https://openalex.org/keywords/natural-language-user-interface","display_name":"Natural language user interface","score":0.41889747977256775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3757299780845642}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8165500164031982},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5868290066719055},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5707131624221802},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5295206904411316},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4935673475265503},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.4536516070365906},{"id":"https://openalex.org/C174252522","wikidata":"https://www.wikidata.org/wiki/Q3816772","display_name":"Natural language user interface","level":3,"score":0.41889747977256775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3757299780845642}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3332710","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3332710","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10318122.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:4a87ad4ce39846af9f33e0946e205ac4","is_oa":true,"landing_page_url":"https://doaj.org/article/4a87ad4ce39846af9f33e0946e205ac4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"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 11, Pp 133681-133702 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3332710","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3332710","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10318122.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8500000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322804","display_name":"Deanship of Scientific Research, King Faisal University","ror":"https://ror.org/00dn43547"},{"id":"https://openalex.org/F4320327702","display_name":"Prince Sultan University","ror":"https://ror.org/053mqrf26"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388666591.pdf","grobid_xml":"https://content.openalex.org/works/W4388666591.grobid-xml"},"referenced_works_count":121,"referenced_works":["https://openalex.org/W26591655","https://openalex.org/W251824417","https://openalex.org/W1503657229","https://openalex.org/W1571393927","https://openalex.org/W1599032155","https://openalex.org/W1968951234","https://openalex.org/W1987680958","https://openalex.org/W1998353461","https://openalex.org/W2009593660","https://openalex.org/W2011447283","https://openalex.org/W2013997717","https://openalex.org/W2019964167","https://openalex.org/W2022146661","https://openalex.org/W2026227174","https://openalex.org/W2026868490","https://openalex.org/W2039009097","https://openalex.org/W2042836586","https://openalex.org/W2054364203","https://openalex.org/W2054959937","https://openalex.org/W2085167231","https://openalex.org/W2085428509","https://openalex.org/W2098162425","https://openalex.org/W2124447821","https://openalex.org/W2128321139","https://openalex.org/W2138453965","https://openalex.org/W2138958299","https://openalex.org/W2157821910","https://openalex.org/W2289072530","https://openalex.org/W2312261674","https://openalex.org/W2314101296","https://openalex.org/W2315821509","https://openalex.org/W2325094964","https://openalex.org/W2335165537","https://openalex.org/W2338320807","https://openalex.org/W2338896872","https://openalex.org/W2399053025","https://openalex.org/W2401672085","https://openalex.org/W2471626172","https://openalex.org/W2490580177","https://openalex.org/W2492019793","https://openalex.org/W2513181925","https://openalex.org/W2522871920","https://openalex.org/W2538807767","https://openalex.org/W2557710000","https://openalex.org/W2558028494","https://openalex.org/W2566319696","https://openalex.org/W2599054872","https://openalex.org/W2604868928","https://openalex.org/W2622489858","https://openalex.org/W2626759941","https://openalex.org/W2743949519","https://openalex.org/W2765104624","https://openalex.org/W2765624302","https://openalex.org/W2767784948","https://openalex.org/W2768030591","https://openalex.org/W2778970600","https://openalex.org/W2783491162","https://openalex.org/W2788121956","https://openalex.org/W2788186240","https://openalex.org/W2799207137","https://openalex.org/W2803891953","https://openalex.org/W2807719128","https://openalex.org/W2883570471","https://openalex.org/W2884326673","https://openalex.org/W2890817238","https://openalex.org/W2890847411","https://openalex.org/W2914324790","https://openalex.org/W2914468586","https://openalex.org/W2916323930","https://openalex.org/W2918520793","https://openalex.org/W2922032333","https://openalex.org/W2930920952","https://openalex.org/W2936946803","https://openalex.org/W2945133413","https://openalex.org/W2963953179","https://openalex.org/W2964956438","https://openalex.org/W2970783892","https://openalex.org/W2971626664","https://openalex.org/W2975777666","https://openalex.org/W2983129300","https://openalex.org/W2990009664","https://openalex.org/W2991918928","https://openalex.org/W2994289934","https://openalex.org/W2995181833","https://openalex.org/W2996005194","https://openalex.org/W3008780766","https://openalex.org/W3009495092","https://openalex.org/W3016313022","https://openalex.org/W3016907511","https://openalex.org/W3043161732","https://openalex.org/W3083920565","https://openalex.org/W3104062721","https://openalex.org/W3115348729","https://openalex.org/W3119450210","https://openalex.org/W3156288252","https://openalex.org/W3158755204","https://openalex.org/W3177222639","https://openalex.org/W3211718567","https://openalex.org/W3215102271","https://openalex.org/W4224282453","https://openalex.org/W4224468222","https://openalex.org/W4231692262","https://openalex.org/W4234919663","https://openalex.org/W4285283104","https://openalex.org/W4286499370","https://openalex.org/W4301602956","https://openalex.org/W4313213856","https://openalex.org/W4394127431","https://openalex.org/W4403308476","https://openalex.org/W6601052559","https://openalex.org/W6679651599","https://openalex.org/W6704004117","https://openalex.org/W6713552389","https://openalex.org/W6729554842","https://openalex.org/W6758911203","https://openalex.org/W6771751565","https://openalex.org/W6772926573","https://openalex.org/W6774501529","https://openalex.org/W6785408966","https://openalex.org/W6873604923","https://openalex.org/W6881546956"],"related_works":["https://openalex.org/W2112751186","https://openalex.org/W3157284875","https://openalex.org/W2147241511","https://openalex.org/W3213549959","https://openalex.org/W2259406085","https://openalex.org/W2401646948","https://openalex.org/W120710326","https://openalex.org/W1543103045","https://openalex.org/W2808455255","https://openalex.org/W2613467614"],"abstract_inverted_index":{"The":[0,107,151],"exponential":[1],"increase":[2],"in":[3,24,39,55,66,83],"textual":[4],"unstructured":[5],"digital":[6],"data":[7,119],"creates":[8],"significant":[9],"demand":[10],"for":[11,162,221],"advanced":[12],"and":[13,36,69,122,147,170,172,182,194],"smart":[14],"stemming":[15,21,46,100,115,157,210],"systems.":[16,57],"As":[17],"a":[18,91,110],"preprocessing":[19],"stage,":[20],"is":[22],"applied":[23],"various":[25,187],"research":[26,200],"fields":[27],"such":[28,56],"as":[29,137,167,199],"information":[30],"retrieval":[31],"(IR),":[32],"domain":[33],"vocabulary":[34],"analysis,":[35],"feature":[37],"reduction":[38],"many":[40],"natural":[41],"language":[42],"processing":[43],"(NLP).":[44],"Text":[45],"(TS),":[47],"an":[48,95],"important":[49],"step,":[50],"can":[51,70,134],"significantly":[52],"improve":[53],"performance":[54,79,185],"Text-stemming":[58],"methods":[59],"developed":[60],"till":[61],"now":[62],"could":[63],"be":[64,135],"better":[65],"their":[67,192],"results":[68],"produce":[71],"errors":[72],"of":[73,80,98,113,186],"different":[74,131,206],"types":[75],"leading":[76],"to":[77,105],"degraded":[78],"the":[81,184,213,217],"applications":[82,208],"which":[84,133,196],"these":[85],"are":[86,197],"used.":[87],"This":[88,202],"work":[89,108,203,219],"presents":[90,109],"systematic":[92],"study":[93,152],"with":[94],"in-depth":[96],"review":[97,112],"selected":[99],"works":[101],"published":[102],"from":[103],"1968":[104],"2023.":[106],"multidimensional":[111],"studied":[114],"algorithms":[116],"i.e.,":[117],"methodology,":[118],"source,":[120],"performance,":[121],"evaluation":[123],"methods.":[124,211],"For":[125],"this":[126],"study,":[127],"we":[128,215],"have":[129,173],"chosen":[130],"stemmers,":[132],"categorized":[136],"1)":[138],"linguistic":[139,155],"knowledge-based,":[140],"2)":[141],"statistical,":[142],"3)":[143],"corpus-based,":[144],"4)":[145],"context-sensitive,":[146],"5)":[148],"hybrid":[149],"stemmers.":[150],"shows":[153],"that":[154],"knowledge-based":[156],"techniques":[158],"were":[159],"widely":[160],"used":[161],"highly":[163],"inflected":[164],"languages":[165],"(such":[166],"Arabic,":[168],"Hindi,":[169],"Urdu)":[171],"reported":[174],"higher":[175],"accuracy":[176],"than":[177],"other":[178],"techniques.":[179],"We":[180],"compare":[181],"analyze":[183],"state-of-the-art":[188],"TS":[189],"approaches,":[190],"including":[191],"issues":[193],"challenges,":[195],"summarized":[198],"gaps.":[201],"also":[204],"analyzes":[205],"NLP":[207],"utilizing":[209],"At":[212],"end,":[214],"list":[216],"future":[218],"directions":[220],"interested":[222],"researchers.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":14}],"updated_date":"2026-06-03T09:05:47.796612","created_date":"2025-10-10T00:00:00"}