Saskia Kuliga

POE 2.0: exploring the potential of social media for capturing unsolicited post occupancy evaluations

This article presents a scoping study in which unsolicited user feedback of the Seattle Public Library was gathered from selected social media and user-review websites to determine the viability of utilizing social media as a novel and unconventional approach to post-occupancy evaluation (POE). Fourteen social media/review websites were surveyed and all available review-data were extracted. This resulted in a rich dataset of almost 500 reviews, which were subjected to further analyses of temporal and geographical patterns, numerical ratings and the semantic content of the reviews. The studys results suggest building users are quite willing to share, without solicitation, their experiences. The results showed: a high proportion of local reviewers (40%); highly regular, temporal patterns of posting, suggesting a sustained interest in reviewing over a period of seven years; numerical ratings suggesting that comments were not dominated by highly opinionated, extreme reviewers but represented a broad range of views; geographical differences in the semantic content of the reviews. The article suggests that highly valuable information is currently available from peer-to-peer networks and that this forms a new class of POE-data which are radically different from current POE paradigms. It concludes that these data might be most valuable through augmenting, and not supplanting, traditional POE.

Machine learning approaches to understand the influence of urban environments on human’s physiological response

Abstract This research proposes a framework for signal processing and information fusion of spatial-temporal multi-sensor data pertaining to understanding patterns of humans physiological changes in an urban environment. The framework includes signal frequency unification, signal pairing, signal filtering, signal quantification, and data labeling. Furthermore, this paper contributes to human-environment interaction research, where a field study to understand the influence of environmental features such as varying sound level, illuminance, field-of-view, or environmental conditions on humans’ perception was proposed. In the study, participants of various demographic backgrounds walked through an urban environment in Zurich, Switzerland while wearing physiological and environmental sensors. Apart from signal processing, four machine learning techniques, classification, fuzzy rule-based inference, feature selection, and clustering, were applied to discover relevant patterns and relationship between the participants’ physiological responses and environmental conditions. The predictive models with high accuracies indicate that the change in the field-of-view corresponds to increased participant arousal. Among all features, the participants’ physiological responses were primarily affected by the change in environmental conditions and field-of-view.