{"id":"https://openalex.org/W2218947495","doi":"https://doi.org/10.48550/arxiv.1410.1135","title":"Corpora Preparation and Stopword List Generation for Arabic data in Social Network","display_name":"Corpora Preparation and Stopword List Generation for Arabic data in Social Network","publication_year":2014,"publication_date":"2014-10-05","ids":{"openalex":"https://openalex.org/W2218947495","doi":"https://doi.org/10.48550/arxiv.1410.1135","mag":"2218947495"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1410.1135","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1410.1135","pdf_url":"https://arxiv.org/pdf/1410.1135","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/1410.1135","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032653144","display_name":"Walaa Medhat","orcid":"https://orcid.org/0000-0001-9482-8412","observed_orcids":["https://orcid.org/0000-0001-9482-8412"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Medhat, Walaa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057744937","display_name":"Ahmed Hassan Yousef","orcid":"https://orcid.org/0000-0002-7799-9233","observed_orcids":["https://orcid.org/0000-0002-7799-9233"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yousef, Ahmed H.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027814033","display_name":"Hoda Korashy","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Korashy, Hoda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9990000128746033,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9990000128746033,"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":0.0006000000284984708,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.00019999999494757503,"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/egyptian-arabic","display_name":"Egyptian Arabic","score":0.5619999766349792},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.984000027179718},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"sentiment analysis","score":0.7689999938011169},{"id":"https://openalex.org/keywords/corpus-preparation","display_name":"corpus preparation","score":0.6690000295639038},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.7699999809265137},{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.7799999713897705},{"id":"https://openalex.org/keywords/bigrams","display_name":"bigrams","score":0.5580000281333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8293470740318298},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.8225279450416565},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7180442810058594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6595492959022522},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6000780463218689},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5613740086555481},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4528544545173645},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.44932302832603455},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.4210623800754547},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3366146683692932},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.21989011764526367},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15749409794807434},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1410.1135","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1410.1135","pdf_url":"https://arxiv.org/pdf/1410.1135","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":"mag:2218947495","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1410.1135","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1410.1135","doi":"https://doi.org/10.48550/arxiv.1410.1135","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1410.1135","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1410.1135","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1410.1135","pdf_url":"https://arxiv.org/pdf/1410.1135","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":[],"sustainable_development_goals_aurora":[{"display_name":"Peace, justice, and strong institutions","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/16"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W194416169","https://openalex.org/W632291594","https://openalex.org/W1550206324","https://openalex.org/W1558725146","https://openalex.org/W1574454071","https://openalex.org/W1634225020","https://openalex.org/W1927021121","https://openalex.org/W1958077162","https://openalex.org/W2019759670","https://openalex.org/W2025618971","https://openalex.org/W2063904635","https://openalex.org/W2086194511","https://openalex.org/W2089065004","https://openalex.org/W2110474840","https://openalex.org/W2113125055","https://openalex.org/W2119759918","https://openalex.org/W2123760808","https://openalex.org/W2145139979","https://openalex.org/W2147272182","https://openalex.org/W2149706766","https://openalex.org/W2166706824","https://openalex.org/W2330587814"],"related_works":["https://openalex.org/W2199735362","https://openalex.org/W4410133728","https://openalex.org/W3081156602","https://openalex.org/W2599005718","https://openalex.org/W3036019901","https://openalex.org/W2978863593","https://openalex.org/W2767285835","https://openalex.org/W3175964988","https://openalex.org/W1995821314","https://openalex.org/W2889965370"],"abstract_inverted_index":{"This":[0],"paper":[1,25,43],"proposes":[2,27],"a":[3,28,32,83,90],"methodology":[4,29],"to":[5,45,93],"prepare":[6],"corpora":[7],"in":[8,78],"Arabic":[9,69],"language":[10,76],"from":[11,35],"online":[12],"social":[13],"network":[14],"(OSN)":[15],"and":[16,89,119,137,141,147],"review":[17],"site":[18],"for":[19,30],"Sentiment":[20],"Analysis":[21],"(SA)":[22],"task.":[23,55],"The":[24,39,56,129,149],"also":[26],"generating":[31],"stopword":[33,84],"list":[34,85,92,124],"the":[36,42,47,53,60,74,97,102,109,121,126,153,157],"prepared":[37],"corpora.":[38,99],"aim":[40],"of":[41,49,86,104,117,167],"is":[44,58,72],"investigate":[46],"effect":[48],"removing":[50],"stopwords":[51,61,169],"on":[52,66],"SA":[54],"problem":[57],"that":[59,152],"lists":[62,111,116,155,166],"generated":[63,82,110,115],"before":[64],"were":[65],"Modern":[67],"Standard":[68],"(MSA)":[70],"which":[71],"not":[73],"common":[75],"used":[77,95],"OSN.":[79],"We":[80,100],"have":[81],"Egyptian":[87,122,158],"dialect":[88,123],"corpus-based":[91],"be":[94],"with":[96,113,125],"OSN":[98],"compare":[101],"efficiency":[103],"text":[105,130],"classification":[106,131],"when":[107],"using":[108,134,165],"along":[112],"previously":[114],"MSA":[118,127,168],"combining":[120],"list.":[128],"was":[132],"performed":[133],"Na\u00efve":[135],"Bayes":[136],"Decision":[138],"Tree":[139],"classifiers":[140],"two":[142],"feature":[143],"selection":[144],"approaches,":[145],"unigrams":[146],"bigram.":[148],"experiments":[150],"show":[151],"general":[154],"containing":[156],"dialects":[159],"words":[160],"give":[161],"better":[162],"performance":[163],"than":[164],"only.":[170]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}