Opinion Mining in Tourism: A Study on “Cappadocia Home Cooking” Restaurant

Opinion Mining in Tourism: A Study on “Cappadocia Home Cooking” Restaurant

Ibrahim Akın Özen (Faculty of Tourism, Nevşehir Hacı Bektas Veli University, Turkey) and Ibrahim Ilhan (Faculty of Tourism, Nevşehir Hacı Bektas Veli University, Turkey)
DOI: 10.4018/978-1-7998-1989-9.ch003

Abstract

In the tourism sector, online tourist reviews analysis is one of the methods to evaluate the products and services offered by businesses and understand the needs of tourists. These reviews take place in social networks and e-commerce sites in parallel with the developments in information and communication technologies. Tourists generate these reviews during or after their use of the products or services. In the literature, these reviews are referred to as UGC (User Generated Content) or eWOM (electronic word-of-mouth). The scientific evaluation of the textual contents in tourist reviews is done by text mining, which is a sub-area of data mining. This chapter discusses the methods and techniques of opinion mining or sentiment analysis. In addition, aspect-based sentiment analysis and techniques to be used in the application are discussed. A case study was carried out using aspect-based sentiment analysis method. In the application “Cappadocia home cooking” restaurant used tourist reviews.
Chapter Preview
Top

Background

In this part, opinion mining or sentiment analysis, sentiment analysis techniques, opinion mining in tourism, challenges of opinion mining in tourism are defined and explained.

Key Terms in this Chapter

NLP (Natural Language Processing): The natural language processing tools can be used to facilitate the SA process. It gives better natural language understanding and thus can help produce more accurate results of SA.

Sentiment Polarity: It is the expression that determines the sentimental aspect of an opinion. In textual data, the result of sentiment analysis can be determined for each entity in the sentence, document or sentence. The sentiment polarity can be determined as positive, negative and neutral.

SVM (Support Vector Machine): It is one of the most effective and simple machine learning methods used in classification. For classification, it is possible to separate the two groups by drawing a boundary between the two groups in one plane. Where this boundary is drawn should be the farthest from the members of both groups. SVM determines how to draw this limit.

Unsupervised Learning: Machine learning is one of the methods. It aims to explore groups within the data that are either non-class or not.

Aspect-Based Sentiment Analysis: is the level of determining opinions in the text analyzed. At this level of analysis, the sentiment polarity is determined separately for each entity or event in the document. Used for detailed document analysis.

Machine Learning: Machine Learning is the general name of computer algorithms (Decision Trees, Naïve Bayes, Logistic Regression, Random Forest) that model a given problem according to the data obtained from the problem environment. Since it is an intensively studied subject, many approaches and algorithms have been proposed.

Supervised Learning: Machine learning is one of the methods. The data is taken from systems that operate on the principle of response to the effect and organized in the input-output order.

Complete Chapter List

Search this Book:
Reset