Sentiment Analysis in Arabic tweets

This dataset was collected to provide Arabic sentiment corpus for the research community to investigate deep learning approaches for Arabic sentiment analysis.

This dataset we collected in April 2019. It contains 58K Arabic tweets (47K training, 11K test) tweets annotated in positive and negative labels. The dataset is balanced and collected using positive and negative emojis lexicon.

Data format: Tab-separated values TSV label

This code is compatible with python 3.x. If python 3 is not default in your system, please using python3 and pip3 commands instead of python and pip commands.

pip install -r requirements.txt

• SciKit-Learn ML algorithms

  • https://www.kaggle.com/mksaad/sentiment-analysis-in-arabic-tweets-using-sklearn

• NLTK Naive Bayes

  • https://www.kaggle.com/mksaad/arabic-sentiment-analysis-in-tweets-nb-bow

  • https://www.kaggle.com/mksaad/arabic-sentiment-analysis-in-tweets-nb-bigrams

https://mksaad.wordpress.com/2018/12/07/sentiment-analysis-in-arabic-tweets-with-python/