{"id":"https://openalex.org/W4297672137","doi":"https://doi.org/10.48550/arxiv.1702.01925","title":"Effects of Stop Words Elimination for Arabic Information Retrieval: A Comparative Study","display_name":"Effects of Stop Words Elimination for Arabic Information Retrieval: A Comparative Study","publication_year":2017,"publication_date":"2017-02-07","ids":{"openalex":"https://openalex.org/W4297672137","doi":"https://doi.org/10.48550/arxiv.1702.01925"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1702.01925","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1702.01925","pdf_url":"https://arxiv.org/pdf/1702.01925","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1702.01925","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034218637","display_name":"Ibrahim Abu El\u2010Khair","orcid":"https://orcid.org/0000-0002-7658-2276","observed_orcids":["https://orcid.org/0000-0002-7658-2276"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"El-Khair, Ibrahim Abu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5034218637"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9965999722480774,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9965999722480774,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.0017000000225380063,"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/T11269","display_name":"Algorithms and Data Compression","score":0.0007999999797903001,"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/arabic-information-retrieval","display_name":"Arabic information retrieval","score":0.9810000061988831},{"id":"https://openalex.org/keywords/inverse-document-frequency","display_name":"inverse document frequency","score":0.8759999871253967},{"id":"https://openalex.org/keywords/probabilistic-retrieval","display_name":"probabilistic retrieval","score":0.7509999871253967},{"id":"https://openalex.org/keywords/retrieval-performance","display_name":"retrieval effectiveness","score":0.597000002861023}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.8763712644577026},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7283896207809448},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6558504104614258},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5730077028274536},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5532766580581665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5440208315849304},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4876021444797516},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4800523519515991},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4204273819923401},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41479700803756714},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.41029587388038635},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13617712259292603},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:1702.01925","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1702.01925","pdf_url":"https://arxiv.org/pdf/1702.01925","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1702.01925","doi":"https://doi.org/10.48550/arxiv.1702.01925","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1702.01925","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1702.01925","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1702.01925","pdf_url":"https://arxiv.org/pdf/1702.01925","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W42789657","https://openalex.org/W2317207408","https://openalex.org/W4312189530","https://openalex.org/W2006477783","https://openalex.org/W61997021","https://openalex.org/W4383104757","https://openalex.org/W121609005","https://openalex.org/W4406487438","https://openalex.org/W7095985004","https://openalex.org/W7100235249"],"abstract_inverted_index":{"The":[0,38,60,75,111],"effectiveness":[1,103],"of":[2,91,114],"three":[3,93],"stop":[4],"words":[5],"lists":[6],"for":[7],"Arabic":[8,65],"Information":[9],"Retrieval---General":[10],"Stoplist,":[11,13],"Corpus-Based":[12],"Combined":[14],"Stoplist":[15],"---were":[16],"investigated":[17],"in":[18,81,97],"this":[19],"study.":[20],"Three":[21],"popular":[22],"weighting":[23,78,94],"schemes":[24],"were":[25],"examined:":[26],"the":[27,43,72,82,87,92,98,108,121],"inverse":[28],"document":[29],"frequency":[30],"weight,":[31],"probabilistic":[32],"weighting,":[33],"and":[34,54],"statistical":[35,44],"language":[36],"modelling.":[37],"Idea":[39],"is":[40],"to":[41,49],"combine":[42],"approaches":[45,48],"with":[46,71,107],"linguistic":[47],"reach":[50],"an":[51],"optimal":[52],"performance,":[53],"compare":[55],"their":[56],"effect":[57],"on":[58],"retrieval.":[59],"LDC":[61],"(Linguistic":[62],"Data":[63],"Consortium)":[64],"Newswire":[66],"data":[67],"set":[68],"was":[69,118],"used":[70,80,96,106],"Lemur":[73],"Toolkit.":[74],"Best":[76],"Match":[77],"scheme":[79],"Okapi":[83],"retrieval":[84,102],"system":[85],"had":[86],"best":[88],"overall":[89,112],"performance":[90,113],"algorithms":[95],"study,":[99],"stoplists":[100],"improved":[101],"especially":[104],"when":[105],"BM25":[109],"weight.":[110],"a":[115],"general":[116],"stoplist":[117],"better":[119],"than":[120],"other":[122],"two":[123],"lists.":[124]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":2}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2022-09-30T00:00:00"}