As South African drivers face the increasing risk of hijackings, data from social network Twitter can be leveraged to develop a map that pinpoints hijacking hot spots.
Speaking at the Southern Africa Telecommunication Networks and Applications Conference (Satnac), hosted by Telkom, University of the Western Cape computer science student Taahir Patel said that, over the last quarter, the country has recorded a steep increase in the number of incidents.
In the period between April and June 2022, 5 866 hijackings were reported across the country, a 14% increase from the previous period.
“The risk of hijackings is becoming greater. But what if there was a way we could mitigate this risk using a platform that people already trust?” says Patel, noting that a social media platform such as Twitter offers a constant flow of real-time information.
Using this stream of up-to-date data, it is possible to visibly plot the occurrence of hijackings on a map that can be used to inform other users, notify emergency responders and even help law enforcement create incident reports.
“The trick is knowing what Twitter data is relevant and what is simply a tweet. Aside from character limit, Twitter does not have many restrictions, so it is crucial that we put the right parameters in place to extract valid data,” he says.
To do this, Patel tested a combination of three machine learning techniques, namely Multilayer Feed-forward Neural Network (MLFNN), Convolutional Neural Network and Bidirectional Encoder Representations from Transformers, to separate the topic of hijacking from actual, relevant incident reports on Twitter.
“The MLFNN technique achieved 98.99% accuracy in determining the validity of tweets as hijacking reports. This is an extremely encouraging result and proves that we can successfully use social media data to develop a map that indicates hijacking hotspots,” says Patel.
Currently, Patel’s work is being turned into a mobile application that can be used to inform the general public of the dangers on the road. However, the opportunities for insights extracted from social media are endless.
Patel is one of 45 computer science and engineering graduates who are presenting at Satnac 2022, a parallel development to the Telkom Centres of Excellence (CoE) programme which provides a platform for future industry leaders to present their research to current industry giants.
Launched in 1997, the CoE programme brings together academia, the telecommunications sector and government to foster the much-needed skills to grow this sector for the greater development of the country.