Affect Measurement: A Roadmap Through Approaches, Technologies, and Data Analysis

Affect signals what humans care about and what matters to them. By providing computers with the capability to measure affect, researchers aspire to narrow the communication gap between the emotional human and the emotionally detached computer, with the ultimate aim of enhancing human–computer interactions. This chapter explores the multidisciplinary foundations of affective state measurement as a multimodal process. Specifically, it: (1) describes popular sensing technologies, including brain–computer interfaces, face-based emotion recognition systems, eye-tracking systems, physiological sensors, body language recognition, and text-based language processing; (2) explores the data gathered from each technology and its key characteristics; (3) outlines the pros and cons of each technology; (4) examines sampling, filtering, and multimodal affective data integration methodologies; and (5) presents the tools and algorithms used to analyze affective data off-line, seeking to make inferences regarding the meaning of that data and to correlate it with stimuli.