Resumen
Recently, extensive studies and research in the Arabic Natural Language Processing (ANLP) field have been conducted for text classification and sentiment analysis. Moreover, the number of studies that target Arabic dialects has also increased. In this research paper, we constructed the first manually annotated dataset of the Emirati dialect for the Instagram platform. The constructed dataset consisted of more than 70,000 comments, mostly written in the Emirati dialect. We annotated the comments in the dataset based on text polarity, dividing them into positive, negative, and neutral categories, and the number of annotated comments was 70,000. Moreover, the dataset was also annotated for the dialect type, categorized into the Emirati dialect, Arabic dialects, and MSA. Preprocessing and TF-IDF features extraction approaches were applied to the constructed Emirati dataset to prepare the dataset for the sentiment analysis experiment and improve its classification performance. The sentiment analysis experiment was carried out on both balanced and unbalanced datasets using several machine learning classifiers. The evaluation metrics of the sentiment analysis experiments were accuracy, recall, precision, and f-measure. The results reported that the best accuracy result was 80.80%, and it was achieved when the ensemble model was applied for the sentiment classification of the unbalanced dataset.