Analyzing Objective and Subjective Data in Social Sciences: Implications for Smart Cities

Abstract

The ease of deployment of digital technologies and the Internet of Things gives us the opportunity to carry out large-scale social studies and to collect vast amounts of data from our cities. In this paper, we investigate a novel way of analyzing data from social sciences studies by employing machine learning and data science techniques. This enables us to maximize the insight gained from this type of studies by fusing both objective (sensor information) and subjective data (direct input from the users). The pilot study is concerned with better understanding the interactions between citizens and urban green spaces. A field experiment was carried out in Sheffield, U.K., involving 1870 participants for two different time periods (7 and 30 days). With the help of a smartphone app, both objective and subjective data were collected. Location tracking was recorded as people entered any of the publicly accessible green spaces. This was complemented by textual and photographic information that users could insert spontaneously or when prompted (when entering a green space). By employing data science and machine learning techniques, we identify the main features observed by the citizens through both text and images. Furthermore, we analyze the time spent by people in parks as well as the top interaction areas. This paper allows us to gain an overview of certain patterns and the behavior of the citizens within their surroundings and it proves the capabilities of integrating technology into large-scale social studies. INDEX TERMS Data analysis, data science, smart cities, social science, urban analytics, urban planning.

Research on the relationship between Urban economic development level and urban spatial structure—A case study of two Chinese cities

“…The method of identifying that based on density is quite subjective [30],because this needs the researchers have a more detailed understanding on the study area to ensure the accuracy of local peak selection, so this approach was inefficient and inaccurate in applying in more cities [31,32]. In recent years, the identification of urban centers and their structures through thermodynamic chart and gridded population distribution has become applicable to most cities and regions [33,34] but if we combine it with the current methods of urban center identification, there are still great subjectivity and uncertainty in the exploration of cities [35].…”

The Center of City Function in Guiyang, China: An Evaluation with Emerging Data

“…These results allowed the center identification program to be applied to numerous cities and regions without requiring much local knowledge. Based on the existing urban center identification methods, the exploration of cities is still subjective and inaccurate [24].…”

Effect of Event-Based Sensing on IoT Node Power Efficiency. Case Study: Air Quality Monitoring in Smart Cities

“…The average consumption of the CPU (C m_ATmega328 ) and the LoRa RF module (C m_LoRa1272 ) depends on the number of measurements taken (one every 15 minutes, or 2,976 per month) and the number of transmissions respectively: (11) to (14), average consumption in the case of periodic transmissions is 77.5 µA for the permanently powered elements, 100 µA for the CPU connecting every 15 minutes to capture and process measurements and 100 µA for the LoRa RF module. The average total consumption for periodic transmissions is 190 µA.…”

“…Sensing is at the heart of Smart Cities, and is used to monitor variables related to a plethora of applications for the environment, health care, transport and mobility, household energy consumption, security and surveillance, etc. [11]. Special mention should be made of battery-powered wireless sensor networks (WSN), due to their capacity for ubiquitous…”