belhayani/darija-sentiment-datasets

# Moroccan Arabic (Darija) Sentiment Analysis Datasets ## Overview Welcome to the Darija Sentiment Datasets repository! This repository is dedicated to providing publicly available datasets for sentiment analysis in the **Moroccan Arabic Dialect (Darija)**. --- ## Table of Contents - Overview - Datasets - Usage - References - Contact ## Datasets | | Dataset | Data source | Size | Labels | Link | Reference | |----|---------------------------------------------------|---------------|-----------------|--------------------|-------------------|-----------| | 1 | ELEC2016 | Facebook | 10254 entries | pos & neg | source | 2017 | | 2 | MSA_MDA | Facebook | 9901 entries | pos & neg | source | 2018 | | 3 | MSAC | Twitter | 2000 entries | pos & neg | source | 2019 | | 4 | MAC | Twitter | 18000 entries | pos, neg, neu, and mix | source | 2021 | | 5 | MSDA | Social Media | 4855 entries | pos, neg, and neu | source | 2023 | | 6 | MYC | Youtube | 20000 entries | pos & neg | source | 2023 | ## Usage You can use these datasets to train, test, and evaluate your sentiment analysis models. Each dataset is available in a structured format (e.g., CSV) with labeled data, making it easy to integrate into machine learning workflows. ## References [[1] Elouardighi, A., Maghfour, M., & Hammia, H. (2017). Collecting and processing arabic facebook comments for sentiment analysis. In Model and Data Engineering: 7th International Conference, MEDI 2017, Barcelona, Spain, October 4–6, 2017, Proceedings 7 (pp. 262-274). Springer International Publ …