Social Media Analytics - Air Transport Network Analysis
Team : Pawanjeet Kaur , Shivam Duseja , Taniya Rajani
Tools used: R, Gephi
Dataset: OpenFlights
This project was done under the guidance of Dr. Ali Tafti. The purpose of this project was to analyse the trends in the air network connecting different source and destinations based on the routes data from open flight.Based on the analysis we reported different hubs in the network,Highest connecting airports, which points are highly connected, how airports are clustered based on different parameteres.
Please read the full description by clicking Read More.
Billions of people take air routes every year and the air industry have a great impact on the world's economy. The airport network is complex with great connectivity secondary if not primary. Hundreds of rural airports have connectivity via intermediate routes. Moreover, this is an interesting area to study network science to understand the world’s connectivity and identify community structures. Complex networks like these are ideal to study network structures aspects like small world phenomena and preferential or random attachment. With rapid growth in air travels, the interest in route optimization has increased. This study can aid in reducing air traffic and optimizing air routes. Our goal is to analyze the characteristics of this network, infer the most connected and visited airports and identify the community structures
To do the analysis various aspect of the network analysis were taken into consideration. We created Gephi plots to understand the linking different nodes and how these links grow or deplete over time. With help of R, we developed ways to find the airports with highest connections i.e. nodes with high degree etc.
After doing complete analysis, below were the key takeaways from the results. The report for this project is attached and is also available on my Git Profile.
Insights and Conclusion
Post analyzing the Air Route Network – we came up with the following insights/conclusions:
• The largest connected component within the network consists of around 98% of the airports (3354 airports).
• Majority of the airports within the network have a degree of less than 20 i.e. most of the airports are connected to less than 20 other airports.
• Airports with the highest degree in the complete network are FRA - Frankfurt airport and CDG - Paris Charles De Gaulle whereas in the largest component we have - ATL -Atlanta airport and LAX -Los Angeles airport.
• Atlanta and LA Airport have the highest betweenness and Eigen vector centrality i.e. these two airports are important in a sense that these airports are linked between other airports most of the time.
• Atlanta Airport followed by London Heathrow Airport are the best hubs wherein Chicago O’Hare airport lies at number 4
• The Air Route network is more vulnerable as compared to the largest connected component within this network.
Code: https://github.com/PawanSran/backup_pawan_mac/tree/master/SPRING%202020/Social%20Media%20and%20Analysis%20-%20IDS%20564/Project_open_flights_dataset