Social Sensing for Sentiment Analysis of Policing Authority Performance in Smart Cities

Abstract

High-tech services in smart cities, ubiquity of smart phones, and proliferation of social media platforms have enabled social sensing, either through direct human observers or through humans as sensor carriers and operators, such as through the use of smart phones, cameras, etc. We performed a sentiment analysis (SA) and mined public opinion on the civil services and policing authority in a smart city. The establishment of high-tech policing in Lahore, Pakistan, known as the Punjab Safe Cities Authority (PSCA), Lahore, along with integrated command and control centers and various equipments, such as 8,000 cameras, monitoring sensors, etc., has resulted in a requirement for its performance evaluation and social media–enabled opinion mining to determine the broader impact on communities. Social sensing of civil services has been enabled through the presence of the PSCA on Facebook, Twitter, YouTube, and Web TV. The SA of the local civil services is not possible without taking into account the local language. In this article, we utilize machine learning techniques to perform multi-class SA of public opinion on policing authority and the provided civil services in both the local languages Urdu and English. The support vector machine provides the highest performance multi-classification accuracy of 86.87% for positive, negative, and neutral sentiments. The temporal sentiments are determined over time from January 2020 to July 2021, with an overall positive sentiment of 62.40% and a negative sentiment of 13.51%, which shows high satisfaction of policing authority and the provided civil services.