A Data Mining Technique for Tourist Destination Brand Image Building

Authors: Alok Aamle, Prof. Mohit Jain

Certificate: View Certificate

Abstract

The destination image branding is the domain of tourism industry where the facts and information is collected and evaluated for finding the credibility of a target tourist destination. Manual collection and processing of collected information accurately is a complicated and time consuming task therefore a data mining model is suggested in this presented work that collect and evaluate the destination image accurately and based on evaluation can make the recommendations about visits of tourist. In order to perform this task data mining techniques are applied on text data source. In first the data is extracted from the Google search engine and it is preprocessed for make it impure. In further the data is labeled based on the positive and negative words available in the collected facts. Finally the clustering and classification of text is performed. For clustering of data FCM (fuzzy c means) clustering algorithm and for classification the Bayesian classifier is used. Based on final classification of text data the decision is made for the destination visits. The implementation of the proposed technique is performed using JAVA technology and their performance is defined using positive and negative probability of prediction. In addition of that the time and space a requirement of the data evaluation is measured which is also acceptable for the proposed application.

Introduction

Data mining and their techniques provides us the ability to analyze the data automatically using the computational algorithms. Additionally grab the outcomes of analysis for decision making, classification, predictions or other essential task. In this presented work the data mining is performed on the unstructured data i.e. text documents. Therefore the proposed work is intended to demonstrate the technique of text mining. The text mining is the sub-domain of data mining that deal with the text data. Using the text mining approaches in this work the destination branding of the tourist places is obtained using text mining techniques. Basically when someone plans to visit some place as tourist he/she not know all the prospects of the particular place. Therefore sometimes the visitor is trapped in various kinds of issues such as misleading place, inappropriate visiting conditions, risk of thief and others. Therefore the visitors collect the information from web to know basics of the particular place. But in most of online resources only the common or basic overview about the places are available. That information is not complete in terms of to make decision to visit the place strongly recommended or not. Therefore in this presented work using the different source of data analysis a new model is proposed that investigates about the places to visit. Additionally by analysis of the data it produces the strong recommendations to the users to visit the place or not. In this context different source of data such as news, blog and other source of data is investigated and analyzed using the data mining algorithms. The analysis of the data results the patterns of data and using the recovered patterns the suggestions are made to visit the place or not.

Conclusion

Destination branding is a subject of tourism industry. In this subject the different source of information is collected for finding the facts about the particular tourist destination. Additionally a brand image is developed on the basis of collected facts about the place goodness. In this context various manual efforts are observed in literature. But the data analysis in manual mode is complicated and time consuming task. Therefore the proposed work include a data mining technique that collect and evaluate the target tourist place for computing the recommendations about the tourist destination brand image. The proposed technique is a data mining model that first employs the Google search engine API for collecting fresh information from web. In next using the positive and negative word list the labeling of data is performed. In final phases two different data mining algorithms are applied for mining and exploring the information and facts. The data mining methods includes the FCM and Bayesian classifier. First using the FCM (fuzzy c means) clustering the data is categorized in two clusters and finally it is classified for finding accurate information about the target place.