Exploring public sentiments for livable places based on a crowd-calibrated sentiment analysis mechanism

Abstract

With the explosion of social networks, people more often share their opinions on-line, which provides a great opportunity to detect the public sentiment of a place in an automatic and timely way comparing to the conventional approaches, e.g., surveys, workshops and interviews. Even through the application of social sentiment analysis is widely discussed in many domains, e.g., politics, e-commerce, economy, and health and environment, to the best of our knowledge, no research has ever studied the effects of public sentiments of social networks in the domain of place design. In order to fill this vacancy, a sentiment analysis service, called geo-sentiment analysis service, is required, whose cores are 1) a social sentiment analysis engine, and 2) an intuitive and interactive visualization service. Thus, this paper firstly proposes CGSA: a Crowd-calibrated Geo-Sentiment Analysis mechanism, which can 1) start the sentiment analysis process based on the design of CTS (Compound Training Samples), and SSF (Social Sentiment Features), 2) perform three analyses, namely sentiment, clustering and time series analysis on geo-tagged social network messages, and 3) collect crowd-labelled data based on a crowdsourced calibration service to gradually improve the classification accuracy. As proved by two detailed analyses, SSF has the best accuracy in training sentiment classifiers, and the performance of the calibrated classifier increases gradually and significantly from 74.71% to 80.05% in three calibration cycles. Moreover, as a part of a big project "Liveable Places", "Sentiment in places" service with two visualization modes, namely 2D sentiment dashboard and 3D sentiment map, is implemented to support local authorities, urban designers and city planners better understand the effects of public sentiments regarding place (re)design in the testbed area: Jurong East, Singapore.