A Framework for Analysing Congestion Hotspots via Social-Media Text-Based Pattern Analysis

This study addresses the escalating traffic congestion crisis in major Indian metropolises such as Mumbai, Pune, Delhi, and Bengaluru. Commuters in these cities experience daily travel times significantly higher than the average in other Asian cities, resulting in an annual economic loss of USD 22 billion, with 12% attributed to reduced productivity. The research proposes a novel approach leveraging social media and geospatial technologies to tackle this issue. By analyzing tweets from official city traffic police handles through the Twitter API and employing Natural Language Processing (NLP) techniques, the study aims to extract location-specific information, conduct sentiment analysis, and visualize traffic hotspots on interactive maps. The resulting congestion map, accessible through online platforms or mobile apps, is expected to empower citizens with real-time information for optimized travel decisions. Authorities can utilize the identified hotspots and location-specific analysis for targeted interventions, including resource allocation, infrastructure improvements, and dynamic traffic signal management. Combining social media data with geospatial analysis, this integrated approach promises to offer a unique perspective on urban traffic dynamics, ultimately contributing to a more efficient, sustainable, and livable urban landscape in India. Additionally, the study delves into the application of text pattern analysis to identify correlations between specific locations and traffic infrastructure-related problems, providing a deeper understanding of the root causes of congestion.