Tourism Analytics
Tourism analytics, also known as Big Data Analytics in Travel and Tourism, refers to a loosely defined set of computationally intensive data mining methods used within tourism research and the tourism industry. The data include spatially explicit data such as information contained within social media, photography, satellite imagery, volunteered geographical information, mobile phone data, eye tracking recording, etc. Methods include GIS analysis, content analysis, sentiment analysis, cluster analysis, traces analysis, machine learning, and many others.
Contents[edit]
1 Description[edit]
Tourism is one of the major sectors of the world economy, generating 10% of GDP globally[1]. As such, businesses within the tourism industry have grown to become quite competitive, requiring them to become proactive in terms of product innovation. Development of new tourism products requires good understanding of tourists' desires, needs, past travel patterns, experiences, personal values, and interactions with other people and environment[2].
Traditionally, this knowledge was generated through methods such as customer surveys, focus groups, or experiments. Recent development and growth of new information and communication technology (ICT) such as mobile phones, radio-frequency identification (RFID) readers, wireless sensor networks, together with the exploding popularity of the social networks generate large volumes of non-structured data, which require special methods of analysis, commonly known as data mining. Frequently this data include geotags, allowing GIS analysis. Tourism analytics hence applies the "knowledge discovery in databases" process (KDD) to Big Data, generated by tourists and tourism businesses to aid marketing, management process, creating new products, and advance knowledge. Examples include:
- Spatial data analysis and visualization with GIS and other geospatial technologies and models (GPS, LiDAR, digital traces, etc.). Examples are mapping of tourist routes and tourist flows, travel photo locations, geo-locations of tweets, emotional mapping, and other spatially distributed social data.
- Analysis of social media (Twitter, Facebook, Instagram and similar platforms), online customer reviews, tourist experiences reported online and other user-generated content.
- Analysis of unstructured data: content analysis of texts, sentiment analysis, analysis of photographs and video.
- People as sensors[3] (digital traces, big data from sensory experiences, Google glasses and similar technologies).
- Big data forecasting and revenue management in hospitality. Website traffic, search engine query volumes, and weather information have been adopted for forecasting hotel occupancies for informing pricing and management decisions in the hospitality and tourism industry[4].
2 Key references[edit]
Marine-Roig and Clave[5] analyzed the texts of 100,000 travel blogs from Barcelona visitors to generate the destination image of the Barcelona brand, coast, and landscapes. That included heritage, leisure and recreation, food and wine, and others. Importantly, in the analysis, the authors found not only the positive feelings (perceptions) associated with the city but also the negative feelings such as related to long waiting in queues. That generated the observed feedback necessary for the development of Barcelona as a "smart destination".
Xiang et al.[6] applied text mining methods to deconstruct over 60,000 Expedia reviews of the US hotels to find the most important issues affecting satisfaction of the hotel customers. Interestingly, hotel maintenance such as cleanliness was found to be the most important.
Radojevich et al.[7] analysed 2,071,007 satisfaction scores posted at Booking.com hotel reservation site by the customers who stayed in 45 capital cities in Europe. In addition to the previous publication, they found that the factors influencing travelers' satisfaction differ between solo travelers, groups of friends, couples, and families.
A new perspective on tourists' preferences can be found from analysis of tourists' photographs. For example, Stepchenkova and Zhan[8] analysed the Flickr photographs made by tourists in Peru and compared the images of the country projected by tourists with those promoted by Peru marketing organizations; one of the interesting outcomes was that the tourists have a strong interest in how Peruvian people live their lives and their everyday activities, which was poorly addressed by the tourism marketing campaigns.
The GPS data on tourists' current location, posted in social networks, can help the cities to project and better manage tourist hot spots and flow between the points of interest (POI). For example, Garcia-Palomares et al.[9] identified tourist hot spots in major European cities from Panoramio photographs.
Universities offering programs in Tourism Analytics[edit]
Following business demand, some universities offer courses in tourism analytics and smart tourism. Temple University offers an online Tourism Analytics Graduate Certificate. The Department of Tourism, Recreation, and Sport Management in the University of Florida offers a graduate level Tourism Analytics program, which includes courses in Smart Design, Advanced Statistics, Data Mining, and GIS. NC State University is developing a Graduate Certificate Program in Tourism Information Management and Advanced Analytics.
4 Further reading[edit]
Xiang, Z., & Fesenmaier, D. R. (2017). Analytics in Smart Tourism Design. Springer, Cham.
Xiang, Z., Schwartz, Z., Gerdes Jr, J. H., & Uysal, M. (2015). What can big data and text analytics tell us about hotel guest experience and satisfaction?. International Journal of Hospitality Management, 44, 120-130.
References[edit]
- ↑ World Travel and Tourism Council (2018). Travel and Tourism Economic Impact 2018 (PDF). Search this book on
- ↑ Xiang, Zheng; Fesenmaier, Daniel R (2017). "Analytics in Smart Tourism Design". Tourism on the Verge. doi:10.1007/978-3-319-44263-1. ISBN 978-3-319-44262-4.
- ↑ Goodchild, Michael F. (2007-11-20). "Citizens as sensors: the world of volunteered geography". GeoJournal. 69 (4): 211–221. CiteSeerX 10.1.1.525.2435. doi:10.1007/s10708-007-9111-y. ISSN 0343-2521.
- ↑ Pan, Bing; Yang, Yang (2017-09-01). "Forecasting Destination Weekly Hotel Occupancy with Big Data". Journal of Travel Research. 56 (7): 957–970. doi:10.1177/0047287516669050. ISSN 0047-2875.
- ↑ Marine-Roig, Estela; Anton Clavé, Salvador (2015-10-01). "Tourism analytics with massive user-generated content: A case study of Barcelona". Journal of Destination Marketing & Management. 4 (3): 162–172. doi:10.1016/j.jdmm.2015.06.004. ISSN 2212-571X.
- ↑ Xiang, Zheng; Schwartz, Zvi; Gerdes, John H; Uysal, Muzaffer (2015-01-01). "What can big data and text analytics tell us about hotel guest experience and satisfaction?". International Journal of Hospitality Management. 44: 120–130. doi:10.1016/j.ijhm.2014.10.013. ISSN 0278-4319.
- ↑ Radojevic, Tijana; Stanisic, Nemanja; Stanic, Nenad (2015-10-01). "Solo travellers assign higher ratings than families: Examining customer satisfaction by demographic group". Tourism Management Perspectives. 16: 247–258. doi:10.1016/j.tmp.2015.08.004. ISSN 2211-9736.
- ↑ Stepchenkova, Svetlana; Zhan, Fangzi (2013-06-01). "Visual destination images of Peru: Comparative content analysis of DMO and user-generated photography". Tourism Management. 36: 590–601. doi:10.1016/j.tourman.2012.08.006. ISSN 0261-5177.
- ↑ García-Palomares, Juan Carlos; Gutiérrez, Javier; Mínguez, Carmen (2015-09-01). "Identification of tourist hot spots based on social networks: A comparative analysis of European metropolises using photo-sharing services and GIS". Applied Geography. 63: 408–417. doi:10.1016/j.apgeog.2015.08.002. ISSN 0143-6228.
This article "Tourism Analytics" is from Wikipedia. The list of its authors can be seen in its historical and/or the page Edithistory:Tourism Analytics. Articles copied from Draft Namespace on Wikipedia could be seen on the Draft Namespace of Wikipedia and not main one.
