Impact of Deep Learning Based Tourism Business Model on Present Tourism Industry

Authors

  • Ms. Harsh Arora, Dr. Mamta Bansal

Abstract

Tourism Industry has become one of the drivers of the worldwide economy and is
continuously increasing over past many years. In the field of tourism, the technology has become so
much advanced these days that tourists always prefer online accessibility of required tourism services.
The availability of data and information over the internet has changed the past accessibility scenario.
Online data and services available in the field of tourism gives a lot of flexibility to the customers to
access the same like online hotel booking and other associated tourism services. This paper focuses on
the impact of deep learning technique by using online customer reviews through sentiment analysis on
tourism business in future. For this purpose, an efficient proposed tourism business model has been
discussed in this paper that will help undoubtedly to enhance the e-business of tourism industry by
imparting more customer satisfaction. The deep learning techniques used for this ensures the
implementation of most efficient methods on tourism data taken online through sentiment analysis.
Further it has been compared with existing techniques of machine learning which shows that deep
learning latest technique RNN using LSTM will give more accurate results worked on customer data
and feedback rather than existing classical machine learning algorithms. So it will remove the barrier of
existing tourism system having gaps and limitations and improved system will come into light in future
to give easy and accurate platform to the customers in context of accessibility of tourism services. More
is customer satisfaction , more will be good reviews about the tourism services of different organizations
that will undoubtedly play utmost important role in enhancing tourism business which is the main
objective of tourism industry and this would be possible only by using current efficient deep learning
technique RNN using LSTM.

Published

2020-11-01

Issue

Section

Articles