Tourism and Social Media

Tourism and Social Media

William B. Claster (Ritsumeikan Asia Pacific University, Japan), Phillip D. Pardo (Ritsumeikan Asia Pacific University, Japan), Malcolm Cooper (Ritsumeikan Asia Pacific University, Japan) and Kayhan Tajeddini (Lund University, Sweden)
Copyright: © 2015 |Pages: 14
DOI: 10.4018/978-1-4666-5888-2.ch358
OnDemand PDF Download:
$30.00
List Price: $37.50

Chapter Preview

Top

Introduction

Data, data, data. Since the advent of mass utilization of personal computers and then the Internet, digitizing of social research has provided us with what previously would have been considered an unreachable quantity of data (Dellarocas, 2003; Lagus et al., 2004). However, the fact that this data is a valuable resource has only recently been recognized. Governments, businesses, and other organizations are just beginning to learn how to turn this data into actionable information and knowledge. Traditionally, manipulation of numeric data was the main purview of analysis, most often derived from sample surveys. Now, with digitization more esoteric analysis has become available in the form of data mining of free-text for comments, attitudes, or sentiment towards objects or concepts of interest to researchers. Free or unstructured text examined through the tools of data mining has been harnessed to produce valuable knowledge that businesses, governments, and researchers can benefit from (Hepburn, 2007; Carson, 2008). For example, analyzing the free text portions of medical records shows that this information can provide new insights into patient and medical staff opinions and reactions that can assist in decision-making in the field of medical tomography (Lee, Koh & Ong, 1989). In this article we will explore this application of data mining to the study of social media and show that valuable and powerful insights generated from these media are also available in the field of tourism and hospitality (Choi et al., 2007; Ellion, 2007; Gretzel et al., 2007).

The analysis of social media can provide the tourism industry with business analytic results in the short term (real-time), medium and longer term horizons (Laboy & Torchio, 2007; Jansen et al., 2009). In this, it is essentially the modern form of ‘word of mouth’, a long established and important method of finding out and influencing decisions in the tourism and hospitality industry (Dellarocas, 2003; Cooper & Eades, 2012). We investigate and describe the real-time potential, industry potential, and brand potential of the methodologies described (Mack et al., 2008; Claster et al., 2010). We also examine whether the tourism and hospitality industry can benefit from real-time monitoring of events through following social media and we investigate how the industry can make use of this knowledge advantage to allow individual businesses to outperform competitors (eMarketer, 2007; Pan et al., 2007; Pang & Lee, 2008; Akehurst, 2009). The utilization of this knowledge resource may lead to lower costs, better differentiation, more effective operational methods, and more powerful innovation in the industry (Werther & Ricci, 2004; Carson, 2005). In addition both comparative and differential advantages may be realized through the use of these methodologies. Current research indicates that social media analytics is a vital tool that must be used to innovate decision support in order to revolutionize the process landscape (Senecal & Nantel, 2004; Tajeddini et al., 2011). It is essential that real-time monitoring be incorporated in overall information strategies; businesses that fail to take advantage of this resource will fall behind and lose market share. In the same way, in addition to real-time monitoring, governments and businesses must learn to take advantage of this resource for its industry development potential and its brand potential. Although our research focuses on the tourism and hospitality industry, we argue that the advantages are fungible and can be applied to many industries and organizations.

Key Terms in this Chapter

Twitter Data: An Application Programming Interface (API) so that developers for external services can get all kinds of information from the Twitter database to use for various purposes. This means external applications can open an active connection to the Twitter server and then receive a constant “stream” of tweets from the server without interruption. This is ideal for applications that require a massive set of real time data for analysis.

Artificial Neural Network: An algorithm which can be used to estimate or classify inputs. Neural networks are capable of machine learning and pattern recognition. They are broadly used in data mining and predictive analytics.

The Naive Bayes Classifier: A means of assigning a class to an input based on a probability assigned to that input and a cut-off value. Its name derives from Bayes Theorem, which is employed in the probability assignment process.

Polarity: The degree of positive or negative sentiment towards the observed object or phenomena. We distinguish this from particular aspects that may be important to the consumer.

Complete Chapter List

Search this Book:
Reset