An Arabic social media based framework for incidents and events monitoring in smart cities



Publication Details

Alkhatib, M., El Barachi, M. & Shaalan, K. 2019, 'An Arabic social media based framework for incidents and events monitoring in smart cities', Journal of Cleaner Production, vol. 220, pp. 771-785.


Smart city initiatives aim at leveraging human, collective, and technological capital to ensure sustainable development and quality of life for their citizens. Offering efficient and sustainable emergency rescue services in smart cities requires coordinated efforts and shared information between the public, the decision makers, and rescue teams. With the rapid growth and proliferation of social media platforms, there is a vast amount of user-generated content that can be used as source of information about cities. In this work, we propose a novel framework for events and incidents' management in smart cities. Our framework uses text mining, text classification, named entity recognition, and stemming techniques to extract the intelligence needed from Arabic social media feeds, for effective incident and emergency management in smart cities. In our system, the data is automatically collected from social media feeds then processed to generate incident intelligence reports that can provide emergency situational awareness and early warning signs to rescue teams. The proposed framework was implemented and tested using datasets collected from Arabic Twitter feeds over a two-years span, and the obtained results show that Polynomial Networks and Support Vector Machines are the top performers in terms of Arabic text classification, achieving classification accuracy of 96.49% and 94.58% respectively, when used with stemming. The results also showed that the use of stemming led to a penalty in terms of response time, and that the richer the dataset/corpus used in terms of size and composition, the higher the classification accuracy will be.

Please refer to publisher version or contact your library.



Link to publisher version (DOI)