In recent years, the strong rise in the use of social network platforms such as Twitter has resulted in millions of users sharing their thoughts and opinions about different aspects and events on the micro-blogging platforms. However, the unfiltered exchange of the content and the missing protection of private information can lead to sending or broadcasting bully and harassment messages in different social media platforms. This kind of messages may have serious negative impact on a person such as causing low self-esteem and depression. Therefore, automatic detection of such messages is more than necessary. This paper casts the problem as a classification task and investigates the effectiveness of deep learning to detect online harassment in Large Human-Labeled corpus specially designed for harassment research purpose. To this end, models are considered namely Long short-term memory(LSTM) ,Bidirectional Long Short-Term Memory (BLSTM),Convolutional neural Network (CNN), and compared with other classification models. Obtained results are very encouraging.