Predicting User Intent from Movie Reviews Using Deep Learning Methods
R. Lokeshkumar1, S. Keerthi2, Aditya Praveen Bora3, K. Jayakumar4
1R. Lokeshkumar, Department of Computer Science, Vellore Institute of Technology, Vellore (Tamil Nadu), India.
2S. Keerthi, Department of Computer Science, Vellore Institute of Technology, Vellore (Tamil Nadu), India.
3Aditya Praveen Bora, Department of Computer Science, Vellore Institute of Technology, Vellore (Tamil Nadu), India.
4K. Jayakumar, Department of Computer Science, Vellore Institute of Technology, Vellore (Tamil Nadu), India.
Manuscript received on 07 April 2019 | Revised Manuscript received on 20 April 2019 | Manuscript published on 30 April 2019 | PP: 386-390 | Volume-8 Issue-6, April 2019 | Retrieval Number: F3528048619/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Intent Detection Plays a Vital Role in Understanding audience sentiment about particular movie. Predicting user in-tent on internet is a problematic task, which requires the combination of multiple sources of information, such as user profile, website activity or user’s internet history. Deep learning plays an important role in text classification as well as in intent detection. Amongst them, most common methods used are recurrent neural networks (RNN) and convolutional neural networks (CNN). In this paper, we use these two deep learning methods to do intent detection on the Rotten Tomatoes dataset and try to tackle the problem of predicting the user intent, based on the reviews given to particular movie. We have compared these two methods based on the accuracy of intent detection as well as the time complexity and performance.
Keyword: Intent Detection, Neural Networks, CNN, RNN.
Scope of the Article: Deep Learning