A Deep Learning Approach for URL Based Health Information Search
R. Rajalakshmi1, S. Ramraj2
1R.Rajalakshmi, Department of Computing Science and Engineering, Vellore Institute of Technology, Chennai (Tamil Nadu), India.
2S.Ramraj, Department of Computing Science and Engineering, Vellore Institute of Technology, Chennai (Tamil Nadu), India.
Manuscript received on 07 March 2019 | Revised Manuscript received on 20 March 2019 | Manuscript published on 30 March 2019 | PP: 642-646 | Volume-8 Issue-5, March 2019 | Retrieval Number: E3306038519/19©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: Nowadays, Internet has become the major source of information for many people in diverse requirements such as Education, Entertainment, Sports, Travel etc. The demand for seeking health information from web has increased drastically over the last two decades. As the content of web is dynamic in nature, the retrieval of relevant health information is challenging. In this research work, an URL based approach is presented to help the user to identify the health related web page. Instead of using the hand crafted features, a deep learning approach is suggested in which the feature learning power of Convolutional Neural Network (CNN) has been exploited to categorize the health relevant web pages. Character level embedding has been suggested for extracting the appropriate features using CNN and these extracted URL features have been used for classification. Various experiments have been carried out on the benchmark data set (Open Directory Project) to analyze the performance of this approach. We have achieved an F1 measure of 83% for this deep learning based approach and the comparative analysis shows that, there is a significant improvement over the existing works.
Keyword: CNN, Deep Learning, Health Information Search, URL Classification
Scope of the Article: Deep Learning