关于OTAs平台上的客户在线评论与酒店业之间的研究 - 2）文献综述

2.0 Literature Review

 

2.1 Introduction

 

Big data analysis is everywhere and has been deeply rooted in daily life. Analyse the relevance, importance, and influence of various industries. As lots of data are being collected, and what is hidden in data analysis has strategic value, big data analysis techniques will continue to innovate and develop in the future (Baesens 2014). This chapter reviews the big data applications in various industries, especially the application literature in the hotel industry. To achieve the purpose of the report research, relevant literature is helpful. This chapter first reviews the achievements of various industries using big data analysis and exploration. Second, understand the literature of hotels using big data to transform and the challenges brought by OTAs. Researching different customer demand from customer reviews on hotels.

 

2.2 Big data analysis

 

Big data analysis collects, and processes large amounts of data characterized by volume, variety, velocity, value and veracity. Its various techniques like clustering, text mining and simulation can be used in the fields of predictive analysis and behavioural analysis and can help companies to analyse key trends or patterns to provide information about their business practices (Revfine 2020).

 

2.3 Application of big data

 

The main goal of the big data application is to collect all types of quantitative and qualitative data from web server logs, Internet clickstream data, social media content and activity reports, or from customer emails, mobile phone details, and machine data captured by multiple sensors (Rouse 2012). And analyse the data to help the company understand its situation and make more informed business decisions (Verma and Agrawal 2016). Nowadays, various industries are following the craze of investing in big data applications, using big data sets to discover all hidden patterns: unknown associations, market trends, customer preferences and other useful business information (Sinha 2019). Examples of how big data may be effectively used in various industries are shown below.

 

2.3.1 Demand forecasting analysis in the transportation industry

 

Demand forecasting analysis in big data analysis can enable transportation companies to better understand how their routes are used, deploy more employees, planes and trains, and be more cost-effective. It is the process of forecasting the demand for products or services so that products or services can be produced and delivered more efficiently and meet customer demand (Rouse 2012). Transportation companies specifically use advanced statistical modelling techniques to analyse sensor data and provide real-time insights into event correlation, root cause analysis, potential risk prediction, and visualisation of possible situations. For example, connecting data, Lufthansa uses big data analysis to predict passenger traffic as accurately as possible. In this case, certain events can be analysed and processed in real-time, such as severe weather, holidays, failures, and customer feedback on operating transportation operations. These data information can be used to plan the operation process more efficiently and economically. Thus, initiate proactive remedial measures to enhance customer service level and experience (Jacobs 2020).

 

2.3.2 Social media analytics in the banking industry

 

Social media tools (such as Twitter, Facebook, YouTube, LinkedIn) and apps are widely accepted, providing new possibilities for using