Evaluating noise perception through online social networks: A text mining approach to designing a noise-event alarm system based on social media content
Abstract
With the rapid rise of the use of Online Social Networks, people have been sharing their opinions and feelings on the Internet: they write about their personal interests and political opinions, but also about their feelings about noisy activities and sounds they hear during their daily life. This textual information could provide policy makers and city managers with insights about the community response towards specific noisy events in cities that may be useful for improving the management of these activities. In this paper, we present a methodology to analyze automatically these Internet opinions by using machine learning and Natural Language processing Technologies. This approach has allowed us to build a system that automatically detects and classifies noise complaints by source, using texts written on online social networks as input. We also present a noise-event alarm system based on statistical process control theory that uses the power of our methodology to detect problematic noise events, as well as the reason why those events caused annoyance to population.
