No abstract

There is growing interest in the field of human-computer interaction in the use of mouse movement data to infer e.g. user's interests, preferences and personality. Previous work has defined various patterns of mouse movement behavior. However, there is a paucity of mouse tracking measures and defined movement patterns for use in the specific context of data collection with online surveys. The present study aimed to define and visualize patterns of mouse movements while the user provided responses in a survey (with questions to be answered using a 5-point Likert response scale). The study produced a wide range of different patterns, including new patterns, and showed that these can easily be distinguished. The identified patterns may -in conjunction with machine learning algorithms -be used for further investigation toward e.g. the recognition of the user's state of mind or for user studies.

There is growing interest in mindfulness-based training of attention. A particular challenge for novices is learning to sustain focused attention while ensuring that the mind does not wander. This paper presents the development of a tool for the automated detection of episodes of mind wandering (MW), on the basis of biosignals, while normal healthy participants engaged in brief mindfulness-based training (BMT) of attention. BMT required five 20-minute training sessions on consecutive days and entailed practice of breath-focused attention, a typical exercise in mindfulness-based techniques of stressreduction. Heart rate, respiratory rate, electrodermal and electromyographic activity were measured, and participants pressed a button to indicate the subjective detection of MW during training. The data showed that BMT did not influence our measures of stress but BMT was effective in reducing the frequency of subjectively detected MW events. The algorithm for offline detection of MW achieved an accuracy of 85%. Based on this algorithm, a mobile application was developed for automated MW detection in real-time. The application requires the use of easily placeable sensors, provides a new approach to the real-time MW detection, and could be developed further for use in MW-related investigations and interventions (such as mindfulness-based training of focused attention). Abstract:There is growing interest in mindfulness-based training of attention. A particular challenge for novices is learning to sustain focused attention while ensuring that the mind does not wander. This paper presents the development of a tool for the automated detection of episodes of mind wandering (MW), on the basis of biosignals, while normal healthy participants engaged in brief mindfulness-based training (BMT) of attention.BMT required five 20-minute training sessions on consecutive days and entailed practice of breath-focused attention, a typical exercise in mindfulness-based techniques of stress-reduction. Heart rate, respiratory rate, electrodermal and electromyographic activity were measured, and participants pressed a button to indicate the subjective detection of MW during training. The data showed that BMT did not influence our measures of stress but BMT was effective in reducing the frequency of subjectively detected MW events. The algorithm for offline detection of MW achieved an accuracy of 85%. Based on this algorithm, a mobile application was developed for automated MW detection in real-time. The application requires the use of easily placeable sensors, provides a new approach to the real-time MW detection, and could be developed further for use in MW-related investigations and interventions (such as mindfulness-based training of focused attention).

No abstract