Feature Extraction through Sentiment Analysis of Tourist Sentiments using Deep Learning Techniques like CNN, RNN and LSTM
Harsh Arora1, Mamta Bansal2

1Ms. Harsh Arora, Research Scholar, Shobhit Deemed University,Meerut, India.
2Dr. Mamta Bansal, Professor, School of Engineering & Technology Department of CSE, Shobhit Deemed University, Meerut, India.

Manuscript received on April 30, 2020. | Revised Manuscript received on May 06, 2020. | Manuscript published on May 30, 2020. | PP: 2254-2261 | Volume-9 Issue-1, May 2020. | Retrieval Number: A2846059120/2020©BEIESP | DOI: 10.35940/ijrte.A2846.059120
Open Access | Ethics and Policies | Cite | Mendeley
© 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: Sentiments are the emotions which are communicated among individuals. These are opinions given by people on any item, product or service availed or experience online. This paper discusses that part of research area which involves the analysis of sentiments exchanged by people online that further tells how sentiments and features through online tourist reviews are extracted using deep learning techniques. Tourist behavior can be judged by tourists reviews for various tourist places, hotels and other services provided by tourism industry. The proposed idea of the paper is to show the high efficiency of deep learning techniques like CNN, RNN,LSTM to extract the features online by use of extra hidden layers. Further, comparison of these techniques as well as comparison of these techniques with machine learning classical algorithms like SVM, Naïve Bayes, KNN,RF etc has been done to show that deep learning methods are more efficient than classical machine learning algorithms. The accurate capturing of attitudes of tourists towards tourist places, hotels & other services of tourism industry plays utmost important role to enhance the business model of tourism industry. This can be done through sentiment analysis using deep learning methods efficiently. Classification of polarity will be done by extracting textual features using CNN,RNN,LSTM deep learning algorithms. Extracting features are fed to deep learning classifier to classify the review into either positive, negative or neutral type of reviews. After comparing various deep learning and classical techniques of machine learning, it has been concluded that LSTM,RNN give best results to classify reviews into positive and negative reviews rather than SVM,KNN classical techniques. In this way sentiment analysis has been done and the proposed idea of this research paper is change in the machine learning techniques or methods from classical algorithms to neural network deep learning methods which in future definitely will give better results to analyze deeply the sentiments of tourists to find out the liking and disliking of various tourist places, hotels and related tourism services that will help tourism business industry to work on the gap in existing services provided by them and system can become more efficient in future. Such improved tourism system will give benefits to tourists or users in terms of better services and undoubtedly it will help tourism industry to enhance business in future.
Keywords: Sentiment analysis, feature extraction, machine learning, deep learning, CNN, RNN, LSTM tourist reviews.
Scope of the Article: Machine Learning