The technological advances of smartphones facilitate the transformation of learning from the classroom to an activity that can happen anywhere and anytime. While micro-learning fosters ubiquitous learning, this flexibility comes at the cost of having an uncontrolled learning environment. To this point, we know little about the usage of mobile learning applications, particularly the occurrence of interruptions and the harm they cause. By diverting users' attention away from the learning task, interruptions can potentially compromise learning performance. We present a four-week in-the-wild study (N = 12) where we investigate learning behavior and the occurrence of interruptions based on device logging and experience sampling questionnaires. We recorded 276 interruptions in 327 learning sessions and found that interruption type as well as users' context influence learning sessions and the severity of the interruption (i.e., session termination likeliness). We discuss challenges and opportunities for the design of automated mechanisms to detect and mitigate interruptions in mobile learning.

The pervasive availability of media in foreign languages is a rich resource for language learning. However, learners are forced to interrupt media consumption whenever comprehension problems occur. We present BrainCoDe, a method to implicitly detect vocabulary gaps through the evaluation of event-related potentials (ERPs). In a user study (N=16), we evaluate BrainCoDe by investigating differences in ERP amplitudes during listening and reading of known words compared to unknown words. We found significant deviations in N400 amplitudes during reading and in N100 amplitudes during listening when encountering unknown words. To evaluate the feasibility of ERPs for real-time applications, we trained a classifier that detects vocabulary gaps with an accuracy of 87.13% for reading and 82.64% for listening, identifying eight out of ten words correctly as known or unknown. We show the potential of BrainCoDe to support media learning through instant translations or by generating personalized learning content.

Ubiquitous technologies change the way we learn new languages. They provide easy access to multilingual media content within everyday scenarios to enhance language skills or improve vocabulary. The detection of learners’ vocabulary deficiencies is an integral part of effective language learning. However, retrieving translations during everyday media consumption causes inattention and hinders fluent learning. In this paper, we investigate Electroencephalography (EEG) to assess single-word incomprehension within non-native learning contents. In a user study (N = 10), we employed Rapid Serial Visual Presentation (RSVP) to display text while recording Event-Related Potentials (ERPs) for different word difficulties. Our results show that incomprehension of words can be detected in participants’ neural responses, as is confirmed by post hoc ratings. We conclude with use case scenarios in which our approach can facilitate seamless vocabulary deficiency detection in everyday life.