Patel, V. L., Kannampallil, T. G., & Kaufman, D. R. (2015). Cognitive Informatics for Biomedicine.
p.128: Computational Ethnography: Automated and Unobtrusive Means for Collecting Data In Situ for Human–Computer Interaction Evaluation Studies — Highlighted Aug 21, 2016
p.132: Combining the ‘thickness’ of ethnographical methods with the strength of automated computational approaches is thus a natural next step for HCI researchers. This new way of collecting behavioral and social data not only forms the basis of the computational ethnography methodology described this chapter, but also the emerging field of “computational social science” at large (Lazer et al. 2009; Giles 2012). In the context of this chapter, we define computational ethnography as “a family of computational methods that leverages computer or sensor-based technologies to unobtrusively or nearly unobtrusively record end users’ routine, in situ activities in health or healthcare related domains for studies of interest to human–computer interaction.” Because computational ethnography is based on data automatically captured through technological means, it by nature provides higher objectivity, less intrusion, more inclusiveness (i.e., into spaces and time where/ when direct observation by human observers is not possible), and better scalability for data collection, aggregation, and analysis. Note that while recording user interactions with a computer system such as keystrokes (Card et al. 1980) and analyzing the behavioral data thus obtained (Ritter and Larkin 1994) have been a widely used study approach in HCI, unless their data are collected in users’ everyday settings via unobtrusive or nearly unobtrusively means (i.e., as opposite to a controlled laboratory environment), such studies do not meet the definition of computational ethnography. Similarly, quantitative observational studies involving independent human observers (e.g., in a time and motion observation) to collect interaction or behavioral data also do not meet the definition of computational ethnography. — Highlighted Aug 21, 2016
p.138: 18.104.22.168 Motion Capture — Highlighted Aug 21, 2016
p.141: A distinctive advantage of using sensor-based technologies such as Kinect is that the data collected can be programmatically analyzed eliminating the need to have human coders to manually review hours of video/audio data. Microsoft provides a non-commercial Kinect Software Development Kit (SDK) freely available to HCI experts to develop customized analytical programs to perform post-processing tasks such as background removal, gesture recognition, facial recognition, and voice recognition.12 — Highlighted Aug 21, 2016