Researchers from King Abdulaziz University in Saudi Arabia — recognizing the wealth of data being generated thanks to the number of connected devices and people’s willingness to give real-time updates of their experiences — believe that harnessing data could one day improve how information concerning traffic, events and other goings-on in a city are understood and disseminated.
As such, the team used Big Data Analytics to locate spatio-temporal events all around London.
"My research was an application towards smart society as a subpart of smart city," said Sugimiyanto Suma, one of the researchers who carried out the study. "It was a workflow design using Apache Spark and Tableau to detect spatio-temporal events in the city, for city awareness, decision making, and city planning. It was based on social media analytics by collecting, processing and analyzing large data from Twitter, which succeeded in detecting events in London with their location dissemination, event name and time."
Using big data and machine learning platforms Spark and Tableau, the team examined over three million Tweets concerning London. Additionally, the team also employed the Google Maps Geocoding application programming interface (API) to detect those Tweeting all around London.
"We found and located congestion around London and empirically demonstrated that events can be detected automatically by analyzing data," Suma said. "We detected the occurrence of multiple events, both their locations and times, including the London Notting Hill Carnival 2017 event, of which we had no prior knowledge."
The research team envisions that the big data analytics workflow could one day be used to help improve decision-making and city planning processes at the government level, and they are currently investigating how to perfect the system with the goal of achieving improved detection accuracy, higher quality analysis and wider spatio-temporal detection.
"For the detection accuracy, we plan to develop algorithms and compare the result with actual information by associating it with events reporting such as news or media websites," Suma explained. "For wider detection, we would acquire more social media data such as Facebook. Finally, for better quality of analysis, we hope to utilize more AI techniques."
The study was published in Smart Societies, Infrastructure, Technologies and Applications.