Sentiment Analysis of Arabic Tweets in Sudanese Dialect

Huda Jamal Abdelhameed, Susana Muñoz- Hernández

Sentiment analysis is the field of science that deals with extracting opinions embedded in human oral or written speech. In this paper we focus on sentiment analysis of Arabic tweets written using either Modern Standard Arabic or Sudanese dialectical Arabic. We have created our own lexicon which contain 2500 words and we have applied three different classifiers on the dataset namely; Support Vector Machine (SVM), Naive Bayes (NB) and K-Nearest Neighbor (K-NN), to classify the tweets based on its polarity into positive or negative. We evaluate our work by four different measures which are Precision, Recall, Accuracy and F-measure. The results show that, SVM achieved the best Recall, Accuracy and F-measure and it equals 95.1%, 76.5% and 84.4% respectively. While NB achieved best Precision and it equals to 85.1%.

https://doi.org/10.31871/IJNTR.5.6.20