Big data generated across social media sites has created numerous opportunities for decision makers. This study aims to design and evaluate a big data analytics method to support strategic decision making in tourism destination management. Using geotagged photos uploaded by travellers to the photo sharing social site, Flickr, the applicability of the method in assisting destination management organisations to analyse and predict tourist behavioural patterns at specific destinations is shown, using Melbourne, Australia as a representative case. The case study demonstrated the ability of the method to identify and predict significant differences between domestic and international tourist patterns, detailed seasonal variations, and visitation patterns relevant to localised demand forecasting. Utility was confirmed using both another destination and directly with stakeholder audiences. Other domains the technology could support include route planning, visitor traffic management and post-visit experience analysis marketing applications. The proposed method is generic, and its applicability to other big data streams is discussed.

1. BIG DATA ANALYTICS FOR
TOURISM DESTINATION
MANAGEMENT
G. Michael McGrath
Professor of Information Systems
Victoria University
Melbourne

2. MOTIVATION
 Travel behavior refer to the actual travel activity
of people during their trips such as spatial and
temporal movement patterns of tourists.
 For examples:
Where do tourists like to visit?
When do tourists visit?
What do tourists like or dislike at each of the
visited locations?
How do tourists travel between places?
What routes do they usually take?
What activities and events do tourists like to
participate in?

3. MOTIVATION
• Such knowledge is valuable for:
– Policy Marker, Government Departments,
Business Managers:
• Destination management
• Product development
• Attraction Development and Marketing
• Tourism Impact management
– Transportation Planners:
• Traffic management
• Transportation Development.

4. MOTIVATION
 Popular methods for capturing travel behavior:
Survey and opinion polls
 Disadvantages:
Time consuming
Limited in terms of the number of responses
Limited in scale of the information captured.
Unable to provide comprehensive understanding
about the locations, time, interests, movement, etc.

5. PROPOSED TECHNOLOGIES
 Many photo-capturing devices now have built-in
global positioning systems (GPS) technology
 Geotagged photos, with embedded time and
geographical information, are shared on social
networking websites such as (but not limited to):

6. PROPOSED TECHNOLOGIES
The geotagged photos have:
 GPS tag (latitude, longitude)
 Taken Time Stamp (Date, Month, Year, Hours, Minutes,
Second)
 Textual Metadata (tags, description, title, comments),
reflecting what people are interested in.
 The Actual Photos, provide insight into tourist’s own
experience about the entities of interest.
 People’s Profile (Where they come from?)
Allow for comprehensive understanding about tourist
behavior without the need of actual engagement.

7. DEMONSTRATION – USING FLICKR DATA
LARGE SCALE STUDY OF HONG KONG
 Photo GPS information viewed on Google Earth.
(approximately 29,443 photos from 2,100 user)

8. DEMONSTRATION
 Area Of Interest Identifications using Clustering

9.  Movement Trajectory generated from geotagged photos.
DEMONSTRATION

10.  Data Collection:
 Big data sets from Social Network such as:
 Data Analysis:
 Develop processing techniques for textual data (review
comments), visual data (travel photos), temporal data (travel
date and time), location data (GPS coordinates), ect….
 Discover Patterns using quantitative data analysis
(statistics, data mining)
DATA DRIVEN APPROACH

11.  Tourist traffic flow Analysis
DEMONSTRATION

12. Actual Route Taken Analysis:
From Center Mong Kok to Time Square Tower
DEMONSTRATION

13.  Time Analysis of Tourist Activity
DEMONSTRATION

14. DEMONSTRATION: LOCATION
PREFERENCE USING GEOTAGGED
PHOTOS FROM FLICKR
Photo Taken by Tourist in Melbourne CBD in July 2015

15. DEMONSTRATION: LOCATION
PREFERENCE USING GEOTAGGED
PHOTOS FROM FLICKR
 Preferred Location to Take sunset photos in Melbourne

16. DEMONSTRATION: LOCATION
PREFERENCE USING GEOTAGGED
PHOTOS FROM FLICKR
 Preferred Location to take Art photos in Melbourne CBD

17. DEMONSTRATION: OUTBOUND
LOCATION PREFERENCE
 Top Visited Cities for Australian Travelers.

18. QUESTIONS
18