Abstract
Many European cities are establishing mandatory obligations for large mobility demand generators such as business and retail parks, tourist sites and events to develop Mobility Management Plans (MMP). Developing MMPs for events with uncertain spatial demand is a particular challenge. This paper investigates whether reliable demand data can be extracted from mining social network (Twitter) content and using the resulting information to inform the design of commercially viable bus routes from periurban areas of Barcelona to a large music event (Canet Rock). Using data from relevant Twitter users, a Twitter
influence score was established for each of the 947 municipalities in the Barcelona Region, providing a spatially distributed picture of the demand to attend the event, prior to event ticket purchase. This was used as the basis
for planning and delivering 11 new commercially viable event bus routes transporting over 450 additional passengers from peri-urban and more rural areas in the Barcelona Region. This paper demonstrates that the innovation of information mining from Social Networks can provide better comprehension of the demand to support Mobility Management Planning for large events and can radically improve the ability of bus services to serve demand from peri-urban and rural areas.
influence score was established for each of the 947 municipalities in the Barcelona Region, providing a spatially distributed picture of the demand to attend the event, prior to event ticket purchase. This was used as the basis
for planning and delivering 11 new commercially viable event bus routes transporting over 450 additional passengers from peri-urban and more rural areas in the Barcelona Region. This paper demonstrates that the innovation of information mining from Social Networks can provide better comprehension of the demand to support Mobility Management Planning for large events and can radically improve the ability of bus services to serve demand from peri-urban and rural areas.
Original language | English |
---|---|
Article number | 103194 |
Number of pages | 15 |
Journal | Transportation Research Part C: Emerging Technologies |
Volume | 128 |
Early online date | 20 May 2021 |
DOIs | |
Publication status | Published - Jul 2021 |
Bibliographical note
AcknowledgmentThe research reflected in this paper has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 770115.
Keywords
- Mobility demand prediction
- Social Media
- User-generated data
- Demand responsive bus
- Mobility management planning