An enhanced corpus for arabic newspapers comments

An enhanced corpus for arabic newspapers comments. Rahab, H., Zitouni, A., & Djoudi, M. International Arab Journal of Information Technology, 17(5):789-798, 2020.
doi abstract bibtex 1 download

In this paper, we propose our enhanced approach to create a dedicated corpus for Algerian Arabic newspapers comments. The developed approach has to enhance an existing approach by the enrichment of the available corpus and the inclusion of the annotation step by following the Model Annotate Train Test Evaluate Revise (MATTER) approach. A corpus is created by collecting comments from web sites of three well know Algerian newspapers. Three classifiers, support vector machines, naïve Bayes, and k-nearest neighbors, were used for classification of comments into positive and negative classes. To identify the influence of the stemming in the obtained results, the classification was tested with and without stemming. Obtained results show that stemming does not enhance considerably the classification due to the nature of Algerian comments tied to Algerian Arabic Dialect. The promising results constitute a motivation for us to improve our approach especially in dealing with non Arabic sentences, especially Dialectal and French ones.

@article{
 title = {An enhanced corpus for arabic newspapers comments},
 type = {article},
 year = {2020},
 keywords = {Arabic,Comment,K-Nearest Neighbours,Naïve Bayes,Opinion mining,Sentiment analysis,Support Vector Machines},
 pages = {789-798},
 volume = {17},
 id = {a18837a0-85fa-33d0-8629-4f3ceb724213},
 created = {2019-08-29T19:36:31.283Z},
 file_attached = {false},
 profile_id = {3f3cebd9-2c9e-33e2-9759-3b3c3deedc23},
 group_id = {6d2dc4f5-aea7-35c9-874f-1d63cc94ab65},
 last_modified = {2021-01-28T22:05:37.480Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {raha_iajit2020},
 source_type = {article},
 private_publication = {false},
 abstract = {In this paper, we propose our enhanced approach to create a dedicated corpus for Algerian Arabic newspapers comments. The developed approach has to enhance an existing approach by the enrichment of the available corpus and the inclusion of the annotation step by following the Model Annotate Train Test Evaluate Revise (MATTER) approach. A corpus is created by collecting comments from web sites of three well know Algerian newspapers. Three classifiers, support vector machines, naïve Bayes, and k-nearest neighbors, were used for classification of comments into positive and negative classes. To identify the influence of the stemming in the obtained results, the classification was tested with and without stemming. Obtained results show that stemming does not enhance considerably the classification due to the nature of Algerian comments tied to Algerian Arabic Dialect. The promising results constitute a motivation for us to improve our approach especially in dealing with non Arabic sentences, especially Dialectal and French ones.},
 bibtype = {article},
 author = {Rahab, Hichem and Zitouni, Abdelhafid and Djoudi, Mahieddine},
 doi = {10.34028/iajit/17/5/12},
 journal = {International Arab Journal of Information Technology},
 number = {5}
}

Downloads: 1

{"_id":"a8ym9rG7Z7Y7bFsFW","bibbaseid":"rahab-zitouni-djoudi-anenhancedcorpusforarabicnewspaperscomments-2020","authorIDs":["5a21deba82d0e44a3e000002","5a38279cecb145c75500003a","5df8c125e6b510df0100010c","5dfa2a821c2129de010000da","5dfa32e01c2129de01000155","5e014af16afa18de01000046","5e01e4211ca64ddf010000b8","5e0e61efac7d11df010000f3","5e199d21204503de010000a5","5e1eead9147729df01000008","5e22317771dcf8df01000130","5e232b16327a15de010000a6","5e2959ae1470eddf0100015a","5e2cfbf76b217bdf01000008","5e36c6ce2bb0d4df01000024","5e36da9c2bb0d4df010000d7","5e397583346d7cde0100016c","5e3acf69f2a00cdf010001d4","5e3fffb017f17dde01000029","5e540b83e81566de0100012b","6TigTE7XwKcbmNFL7","6eSYnAebLFYsBihpB","9yyRDvfffSAkAFXrr","BfqDE9PspPR3ByqTo","FCzDkfHtMmcFANpKx","HRKdyeSzR3o7eMNw7","K4fcy9kt8sZgG6oj9","Y5ExTeNBYWDkytzSJ","YLg4oQgy66arvtkhM","b7s3doyTZbx4nmB5T","c7b6nNs4AxsHiECSJ","co4WY3mhXGzL4qz7M","eBrLGQWyHaAcb7mcg","memJXMs9ZdgssW6Wk","npCZ7PxPxwZXtdG5u","oYMYYjJmEkqjP4CKB","pZcmqhLCPoQ28Y2bv","qer2TDtSZHi5pN8jL","r7yhPWHjm6oGvzkg2","rwyFcjMsp5qKZaQ3e","zmGaX3RvABytnLJK8"],"author_short":["Rahab, H.","Zitouni, A.","Djoudi, M."],"bibdata":{"title":"An enhanced corpus for arabic newspapers comments","type":"article","year":"2020","keywords":"Arabic,Comment,K-Nearest Neighbours,Naïve Bayes,Opinion mining,Sentiment analysis,Support Vector Machines","pages":"789-798","volume":"17","id":"a18837a0-85fa-33d0-8629-4f3ceb724213","created":"2019-08-29T19:36:31.283Z","file_attached":false,"profile_id":"3f3cebd9-2c9e-33e2-9759-3b3c3deedc23","group_id":"6d2dc4f5-aea7-35c9-874f-1d63cc94ab65","last_modified":"2021-01-28T22:05:37.480Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"raha_iajit2020","source_type":"article","private_publication":false,"abstract":"In this paper, we propose our enhanced approach to create a dedicated corpus for Algerian Arabic newspapers comments. The developed approach has to enhance an existing approach by the enrichment of the available corpus and the inclusion of the annotation step by following the Model Annotate Train Test Evaluate Revise (MATTER) approach. A corpus is created by collecting comments from web sites of three well know Algerian newspapers. Three classifiers, support vector machines, naïve Bayes, and k-nearest neighbors, were used for classification of comments into positive and negative classes. To identify the influence of the stemming in the obtained results, the classification was tested with and without stemming. Obtained results show that stemming does not enhance considerably the classification due to the nature of Algerian comments tied to Algerian Arabic Dialect. The promising results constitute a motivation for us to improve our approach especially in dealing with non Arabic sentences, especially Dialectal and French ones.","bibtype":"article","author":"Rahab, Hichem and Zitouni, Abdelhafid and Djoudi, Mahieddine","doi":"10.34028/iajit/17/5/12","journal":"International Arab Journal of Information Technology","number":"5","bibtex":"@article{\n title = {An enhanced corpus for arabic newspapers comments},\n type = {article},\n year = {2020},\n keywords = {Arabic,Comment,K-Nearest Neighbours,Naïve Bayes,Opinion mining,Sentiment analysis,Support Vector Machines},\n pages = {789-798},\n volume = {17},\n id = {a18837a0-85fa-33d0-8629-4f3ceb724213},\n created = {2019-08-29T19:36:31.283Z},\n file_attached = {false},\n profile_id = {3f3cebd9-2c9e-33e2-9759-3b3c3deedc23},\n group_id = {6d2dc4f5-aea7-35c9-874f-1d63cc94ab65},\n last_modified = {2021-01-28T22:05:37.480Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {raha_iajit2020},\n source_type = {article},\n private_publication = {false},\n abstract = {In this paper, we propose our enhanced approach to create a dedicated corpus for Algerian Arabic newspapers comments. The developed approach has to enhance an existing approach by the enrichment of the available corpus and the inclusion of the annotation step by following the Model Annotate Train Test Evaluate Revise (MATTER) approach. A corpus is created by collecting comments from web sites of three well know Algerian newspapers. Three classifiers, support vector machines, naïve Bayes, and k-nearest neighbors, were used for classification of comments into positive and negative classes. To identify the influence of the stemming in the obtained results, the classification was tested with and without stemming. Obtained results show that stemming does not enhance considerably the classification due to the nature of Algerian comments tied to Algerian Arabic Dialect. The promising results constitute a motivation for us to improve our approach especially in dealing with non Arabic sentences, especially Dialectal and French ones.},\n bibtype = {article},\n author = {Rahab, Hichem and Zitouni, Abdelhafid and Djoudi, Mahieddine},\n doi = {10.34028/iajit/17/5/12},\n journal = {International Arab Journal of Information Technology},\n number = {5}\n}","author_short":["Rahab, H.","Zitouni, A.","Djoudi, M."],"biburl":"https://bibbase.org/service/mendeley/3f3cebd9-2c9e-33e2-9759-3b3c3deedc23","bibbaseid":"rahab-zitouni-djoudi-anenhancedcorpusforarabicnewspaperscomments-2020","role":"author","urls":{},"keyword":["Arabic","Comment","K-Nearest Neighbours","Naïve Bayes","Opinion mining","Sentiment analysis","Support Vector Machines"],"metadata":{"authorlinks":{"djoudi, m":"http://djoudi.online.fr/articles.php","djoudi, m":"http://djoudi.mahieddine.online.fr/articles.php","zitouni, a":"https://bibbase.org/service/mendeley/3f3cebd9-2c9e-33e2-9759-3b3c3deedc23/group/6d2dc4f5-aea7-35c9-874f-1d63cc94ab65"}},"downloads":1},"bibtype":"article","creationDate":"2019-08-29T19:36:47.894Z","downloads":1,"keywords":["arabic","comment","k-nearest neighbours","naïve bayes","opinion mining","sentiment analysis","support vector machines"],"search_terms":["enhanced","corpus","arabic","newspapers","comments","rahab","zitouni","djoudi"],"title":"An enhanced corpus for arabic newspapers comments","year":2020,"biburl":"https://bibbase.org/service/mendeley/3f3cebd9-2c9e-33e2-9759-3b3c3deedc23","dataSources":["rh94BkjSH73SyjZsR","ya2CyA73rpZseyrZ8","o6H2FdNemGj2A9Rsq","iepCnBefzQg3Bw5fo","B9CSJFaMFh3P3584A","G2mFzxcNhwvPwybbi","PgsKQnKXuGehwfH4n","GLMs4nYirTtANpSJL"]}