Towards a New Lexicon-Based Features Vector for Sentiment Analysis: Application to Moroccan Arabic Tweets

An analysis of customer perception using lexicon-based sentiment analysis of Arabic Texts framework

“…These metrics include Accuracy (Acc), Precision (P), Recall (R), and F1-score (F1). They are calculated based on the confusion matrix metrics True Positive (TP), False Positive (FP), True Negative (TN) and False Negative (FN) [ 29 ].…”

“…The integration of lemmatization using the Qalasadi Arabic Morphological Analyses library contributes to improving the accuracy and comprehensiveness of the LSAnArTe Framework for Arabic text. It enables the identification of sentiment-related words even when they appear in different inflected or derived forms [ 29 ]. This will be elaborated further in the Performance Evaluation section.…”