Word-Level vs Sentence-Level Language Identification: Application to Algerian and Arabic Dialects

In this paper, we investigate a set of methods for textual Arabic Dialect Identification, where we considered word-level and sentence-level approaches. We used three classifiers, namely: Linear Support Vector Machine L-SVM, Bernoulli Naive Bayes BNB and Multinomial Naive Bayes MNB. Then we combined them by using a voting procedure. We carried out experiments on two sets of dialects: the first one, PADIC, which consists of parallel sentences in Maghrebi and Middle Eastern dialects; and the second, a set of Algerian dialects only, that we built manually. For the Arabic dialects, we obtained an average accuracy of 92%. For Algerian dialects, our approach yielded an average accuracy of about 76%.