Data Analytics for Predicting Situational Developments in Smart Cities: Assessing User Perceptions.

Area of Science:

• Urban Planning
• Social Science
• Data Science

Background:

• Analyzing large, diverse datasets is crucial for megacity development and smart city initiatives.
• Real-time assessment of citizen sentiment and social tension is vital for urban project success.
• Existing methods may not adequately capture the nuances of public opinion in dynamic urban environments.

Purpose of the Study:

• To develop and test algorithms for analyzing social media data to gauge citizen opinions.
• To verify and examine data for social tension analysis and situation prediction during urban project implementation.
• To provide actionable recommendations for conflict aversion and social tension mitigation in urban development.

Main Methods:

• Utilized an interdisciplinary approach integrating social media, blogs, forums, and review sites.
• Employed data analysis tools including Brand Analytics, TextAnalyst 2.32, GPT-3.5, GPT-4, GPT-4o, and Tableau.
• Applied algorithms to real-time social media data from a transportation system development project.

Main Results:

• Data analysis revealed a neutral public perception of the urban transportation project.
• Identical outcomes across multiple analytical tools confirmed the absence of social tension.
• The study successfully predicted a calm development trajectory for the project situation.

Conclusions:

• The developed algorithms effectively assess citizen sentiment and social tension in real-time.
• Proactive identification and mitigation of social tension are key for successful urban project implementation.
• Data-driven insights support informed decision-making to enhance urban quality of life.