Chen G., Yu L., Ng W.S., Wu H., Kunasegaran U.N. (2017) STA: A Spatio-Temporal Thematic Analytics Framework for Urban Ground Sensing. In: Cong G., Peng WC., Zhang W., Li C., Sun A. (eds) Advanced Data Mining and Applications. ADMA 2017. Lecture Notes in Computer Science, vol 10604. Springer, Cham
Abstract:
Participatory planning is a relative new urban planning paradigm where public’s feedback is considered as part of urban planning processes. The primary challenge is to systematically summarize the large texture content of the collected public’s feedback and generates insightful information for city planners. This process is called “Ground Sensing”. In this paper, we developed a more general urban-centric feedback analysis framework, which encompasses the spatio-temporal thematic (where, when, what) of ground sensing. Three essential methods: geotagging, topic modeling, and trend analysis of ground sensing are proposed and a prototype has been implemented. Results of experiments on the effectiveness of the proposed methods are presented using real-world urban planning data. The results indicate that the method of integrating the geotagging tool and machine learning techniques can accurately extract precise geospatial information. Also, thematic analysis based on a probabilistic topic modeling with Latent Dirichlet Allocation provides a quick and comprehensive understanding of the massive ground concerns of the public and hence improve the decision-making process. Importantly, the spatial and temporal trends of detected topics could not only indicate the effectiveness of our proposed algorithm, but also benefit domain experts in their routine work and reveal many interesting insights on ground sensing matters.