Prosody has been widely used in many speech-related applications including speaker and word recognition, emotion and accent identi cation, topic and sentence segmen- tation, and text-to-speech applications. An important application we investigated, is that of identifying question sentences in Arabic monologue lectures. Languages other than Arabic have received a lot of attention in this regard. We approached this prob- lem by rst segmenting the sentences from the continuous speech using intensity and duration features. Prosodic features are then extracted from each sentence. These fea- tures are used as input to decision trees to classify each sentence into either Question or Non Question sentence. Our results suggest that questions are redundantly marked in natural Arabic speech and automatically extracted prosodic features can make signi cant contribu-tion in question identi cation. We classi ed Questions with an accuracy of 77.43%. Feature speci c analysis further reveals that energy and fundamental frequency (F0) features are mainly responsible for discriminating between question and non-question sentences. We found that Bayes Network performed better than SVM, MLP and Decision Trees on our dataset. Removal of correlated features through Correlations Based Feature Selection (CFS) produced more e cient and accurate results than the complete feature set.