A Novel Aspect Based Framework for Tourism Sector with Improvised Aspect and Opinion Mining Algorithm

Abstract

With the growth of e-commerce web sites, the demand of writing reviews on these portals have gained huge popularity. This huge data must be mined to analyze the opinion and for making better decisions in different domains. In this paper, we have proposed an aspect based opinion mining algorithm for the tourism domain. It first determines the aspects, and then extracts the opinion words related to the aspects. The opinion words are provided a score based on the Senti-Wordnet and the final score of each aspect is calculated by the summation of the scores of the opinions. The final score is visualized depicting ranking of scores of different aspects for different hotels.