From info to insight: Smart City mobility sensing
Citibeats’ #Barcelona case study on city mobility
According to the Fraunhofer Center for Smart Cities, “the public transportation system is the lifeline of a smart city”. More and more, as cities implement congestion charges or other deterrents towards driving, and their citizens recognize the value of sharing transport resources, public transport is becoming the key mobility issue of city spaces. Eurostat give an example: in France, the national average of citizens who use public transport to get to work is 17.8%. But in the largest city, Paris, this figure skyrockets to 69.4%. Public mobility is at the heart of urban life.
Smart cities mean smart mobility
City mobility faces a number of challenges. Transport infrastructures are limited by space and existing resources. As traffic increases, existing traffic management systems are often inadequate. Parking spaces are limited and often difficult to find, which wastes time and fuel. A growing number of public trains, buses and shared bikes all need to be maintained, repaired, and checked. And to meet environmental goals, CO2 emissions must be reduced.
One smart solution is the Internet of Things, where objects are connected to the web, sending and receiving data. Cars, buses, trains, bikes, traffic lights, tickets, parking spaces: these can all be digitized, to create an integrated information flow between the citizens who use these objects, the organizations that manage them, and the governments who make mobility decisions. The next development here, according to Robin Chase, is the Internet of Moving Things. She says: “the real long-term potential lies in the data generated by sensors being installed on cars and transportation infrastructure, which could be tapped for new insights on fleet management, heavily-trafficked corridors, peak drive times and other transit metrics.”
From information to insight
IoT data is changing the world of mobility. But the numbers-based information it provides is only half of the city’s story. At citibeats, our mission is to turn information into insight. Our machine-learning technology processes natural language data taken from sources like social media. We go beyond the numbers to track citizens’ opinions, concerns, explanations and feelings.
citibeats technology adds human meaning to mobility data.
IoT city sensors raise questions that citibeats answers. For example: the data this week says there has been a 10% increase in parking shortages in a particular neighborhood. Why? Should city leaders invest in more parking? By analyzing what citizens are saying, we might find out that this is due to a one-off concert, and no action is needed. Or, we might see that this is a top mobility concern for citizens, that is getting worse each week. This lets city leaders make sense of problems, and make smarter decisions.
But citibeats also anticipates problems. When things are going okay, it’s time to think about future issues, and focus on predictive maintenance. In these cases, we might see that citizens’ #1 long term concern is confusing road signs, in one specific area. Or lack of adequate trains at a particular time of day. The citibeats dashboard categorises and compares priorities, tracks sentiment spikes, and identifies the most representative opinions on a topic.
Case study: Barcelona
So we put it to the test. In December 2017, citibeats analyzed 30,000 mobility-related Tweets in Barcelona, to understand the concerns of over 15,000 citizens. Here’s what we found.
Public transport is the top mobility concern for Barcelona citizens, mentioned in 49% of mobility Tweets.
The single biggest public transport concern during this period was an increase in train ticket prices. Many citizens felt the increase was related to the current political crisis.
Citizens also had positive things to say about mobility. The positive conversation mostly revolved around local taxis: Barcelona residents showed support for local taxis, and sought to campaign against Uber and Cabify. 38% of sentiment expressed about taxis was positive – the highest of any mobility category.
But overall, 29% of transit sentiment was strongly negative, suggesting lots of room to improve.
In the Barcelona mobility case study, the data highlights the need for better ways to communicate and manage public transport price increases, and to tap into citizens’ support for local transport like taxis. This kind of information allows city leaders to really listen to their citizens. By tracking transit issues beyond the numbers, they can understand how city residents really feel and act to build smart, mobile cities.