This paper discusses a framework used to detect sarcasm in relation to time. It uses a set of deep learning extracted features (deep features) combined with a set of handcrafted features. The results of the experiments are positive in terms of Accuracy, Precision, Recall and F1-measure. The combination of features is classified using a few machine learning techniques for comparison purposes. Logistic Regression is found to be the best classification algorithm for this task with an accuracy of 89%. Furthermore, result comparison to recent works and the performance of each feature set are also shown as additional information.