Term-Relevance Prediction from Brain Signals (TRPB) is proposed to automatically detect relevance of text information directly from brain signals. An experiment with forty participants was conducted to record neural activity of participants while providing relevance judgments to text stimuli for a given topic. High-precision scientific equipment was used to quantify neural activity across 32 electroencephalography (EEG) channels. A classifier based on a multi-view EEG feature representation showed improvement up to 17% in relevance prediction based on brain signals alone. Relevance was also associated with brain activity with significant changes in certain brain areas. Consequently, TRPB is based on changes identified in specific brain areas and does not require user-specific training or calibration. Hence, relevance predictions can be conducted for unseen content and unseen participants. As an application of TRPB we demonstrate a high-precision variant of the classifier that constructs sets of relevant terms for a given unknown topic of interest. Our research shows that detecting relevance from brain signals is possible and allows the acquisition of relevance judgments without a need to observe any other user interaction. This suggests that TRPB could be used in combination or as an alternative for conventional implicit feedback signals, such as dwell time or click-through activity.

No abstract

Digital monitoring of physiological signals can allow computer systems to adapt unobtrusively to users, so as to enhance personalised 'smart' interactions. In recent years, physiological computing has grown as a research field, and it is increasingly considered in diverse applications, ranging from specialised work contexts to consumer electronics. Working in this emerging field requires comprehension of several physiological signals, psychophysiological states or 'indices', and analysis techniques. The resulting literature encompasses a complex array of knowledge and techniques, presenting a clear challenge to the practitioner.We provide a foundational review of the field of psychophysiology to serve as a primer for the novice, enabling rapid familiarisation with the core concepts, or as a quick-reference resource for advanced readers. We place special emphasis on everyday human-computer interface applications, drawing a distinction from clinical or sports applications, which are more commonplace. The review provides a framework of commonly understood terms associated with experiential constructs and physiological signals. Then, 12 short and precisely focused review chapters describe 10 individual signals or signal sources and present two technical discussions of online data fusion and processing. A systematic review of multimodal studies is provided in the form of a reference table. We conclude with a general discussion of the application of psychophysiology to human-computer interaction, including guidelines and challenges.

The use of psychophysiologic signals in human-computer interaction is a growing field with significant potential for future smart personalised systems. Working in this emerging field requires comprehension of different physiological signals and analysis techniques. Cardiovascular signals such as heart rate variability and blood pressure variability are commonly used in psychophysiology in order to investigate phenomena such as mental workload. In this paper we present a short review of different cardiovascular metrics useful in the context of humancomputer interaction. This paper aims to serve as a primer for the novice, enabling rapid familiarisation with the latest core concepts. We emphasise everyday humancomputer interface applications to distinguish from the more common clinical or sports uses of psychophysiology. This paper is an extract from a comprehensive review of the entire field of ambulatory psychophysiology, with 12 similar chapters, plus application guidelines and systematic review.