Academic journal article Contemporary Management Research

Using Big Data and Text Analytics to Understand How Customer Experiences Posted on Yelp.com Impact the Hospitality Industry

Academic journal article Contemporary Management Research

Using Big Data and Text Analytics to Understand How Customer Experiences Posted on Yelp.com Impact the Hospitality Industry

Article excerpt

INTRODUCTION

Big data has become a popular area of research with the potential to add huge value of products and services to industry and business (Ang & Seng, 2016). The changing rate of generated data comes from the rapid growth of Internet of Things, cloud computing, and efficacy improvement of the search engine, leading to the growth of big data and more opportunities for data centers (Mehdipour, Noori, & Javadi, 2016). Big data analytics focuses on the collection of data with an unprecedented breadth, scale, and depth to solve actual problems (Mayer-Schonberger & Cukier, 2014). The increasing need to solve such problems is driven by companies such as Facebook, Google, LinkedIn that have to find a way to feed large-scale analytic engines to produce additional value services such as recommender systems, customer analytics, and social network analytics (Ang & Seng, 2016). At the same time, many social media websites, especially in the hospitality industry, that operate booking services produce large quantities of user-generated data. Researchers hope to use this this data to gain insights into research problems which have not well been understood by traditional methods (Yang, Pan, & Song, 2014). Indeed, over the past few decades, businesses have generated more web data than they can or know how to use (Fayyad, Piatetsky-Shapiro, & Smyth, 1996). Therefore, analyzing primary data from individual consumers will lead to entirely new ways of understanding consumer behavior and formulating marketing strategy (Erevelles, Fukawa, & Swayne, 2016). The goal of this study is to explore the possible utility of online guest reviews by using big data analytics to finding the important text of different hotel that have not yet been studied. User-generated content in the hospitality industry, which in this study is online customer reviews, could cover many topics of interest to hotel managers because it contributes to electronic word-of-mouth (e-WOM) information (Bailey, 2005), customer loyalty, and reach purchase decisions in relation to tourism and hospitality products and services (Browning, So, & Sparks, 2013). The hotel industry offers highly competitive services and products, so each hotel must distinguish itself. Customer satisfaction has therefore become a key factor in measuring a company's competitiveness and success (Bitner & Hubbert, 1994). Although many studies have used customer reviews to explore reprehensive factors to understand the components of and the relationship of guest satisfaction (Wu & Liang, 2009), and suggest different viewpoints on e-mouth of mouth research, most studies have relied on conventional methods such as focus group interviews or customer surveys to gauge what leads to guest satisfaction (Xiang, Schwartz, Gerdes, & Uysal, 2015). Therefore, whether we can explore meaningful insights into customer experience related to guest reviews, using big data as a new research method to decode the hospitality meaning in it is an important research question.

This study uses online customer reviews to gain behavioral insights about consumers and to find the useful keywords. Customer reviews are collected from Yelp.com and text analytics is used to explore the answer. These data mining methods could find the meaningful structure of customer reviews when customers assign a rating and post a comment about a hotel at which they have stayed.

This study is structured as follows. After the introduction, the second section reviews the literature on big data, text analytics, hotel guest experience and customer reviews. Two research questions are formulated and explored to understand the meaning of customer reviews. The section on research method details the data collection and the text mining techniques that are used to answer the research questions. The results are then presented. Finally, the study's contributions to practice and literatures as in addition to directions for future research and limitation are discussed. …

Search by... Author
Show... All Results Primary Sources Peer-reviewed

Oops!

An unknown error has occurred. Please click the button below to reload the page. If the problem persists, please try again in a little while.