Lately, the use of the Internet has led to an increase in social networking sites. The world has become an open environment, and social networking sites have been increasingly used to exchange medical experiences, and they have been adopted in many cases as basic references in obtaining medical advice, which has led to the misuse of medicines. A growing problem, abuse of prescription medications can have a negative impact on all age groups and come with adverse health consequences, as individuals in societies become susceptible to many drug interactions and serious side effects and reduced drug efficacy, which makes a simple health problem turn into a complex health problem; our study aims to classify drug use in Arabic content in social media (use, abuse) by using both Machine Learning (ML) algorithms and AraBERT model. Many studies detect the drug abuse in the English language. There are no studies on Arabic language. Arabic social media dataset was created from Facebook with nearly 7,000 posts. We used different ML classifiers; the most famous of them are Support Vector Machine (SVM), Decision Tree (J48), Naive Bayes (NB), K-Nearest Neighbor (KNN) and Random Forest (RF). We also applied AraBERT based model; CNN-AraBERT, RNN-AraBERT, and LSTM-AraBERT. The classifier's accuracy was evaluated by calculating the F1-Measure, Recall, and Precision measurements. The results indicated that CNN-AraBERT classifier is given the highest value of F1-Measure for Facebook dataset for both classification tasks with (98.3%) for binary classification and (90.99%) for multi-classification.