Abstract:Reading is central to learning and communicating, however, divided attention in the form of distraction may be present in learning environments, resulting in a limited understanding of the reading material. This paper presents a novel system that can spatio-temporally detect divided attention in users during two different reading applications: typical document reading and speed reading. Eye tracking and electroencephalography (EEG) monitor the user during reading and provide a classifier with data to decide th… Show more
“…For instance, the stable “in the zone” state in gradCPT was shown to be related to moderate DMN activity. On the other hand, CS researchers usually focused on different aspects of attention stimuli and defined attention within a specific context [ 11 , 89 , 90 ], e.g., the divided attention research in video learning [ 11 ] focused on only two stimuli of distraction—multitasking and environmental noise—and this potentially limits its generalization to other contexts. In our work, we distinguish attention states based on a RTV analysis in gradCPT, depending less on distractions or other environmental factors.…”
While numerous studies have explored using various sensing techniques to measure attention states, moment-to-moment attention fluctuation measurement is unavailable. To bridge this gap, we applied a novel paradigm in psychology, the gradual-onset continuous performance task (gradCPT), to collect the ground truth of attention states. GradCPT allows for the precise labeling of attention fluctuation on an 800 ms time scale. We then developed a new technique for measuring continuous attention fluctuation, based on a machine learning approach that uses the spectral properties of EEG signals as the main features. We demonstrated that, even using a consumer grade EEG device, the detection accuracy of moment-to-moment attention fluctuations was 73.49%. Next, we empirically validated our technique in a video learning scenario and found that our technique match with the classification obtained through thought probes, with an average F1 score of 0.77. Our results suggest the effectiveness of using gradCPT as a ground truth labeling method and the feasibility of using consumer-grade EEG devices for continuous attention fluctuation detection.
“…For instance, the stable “in the zone” state in gradCPT was shown to be related to moderate DMN activity. On the other hand, CS researchers usually focused on different aspects of attention stimuli and defined attention within a specific context [ 11 , 89 , 90 ], e.g., the divided attention research in video learning [ 11 ] focused on only two stimuli of distraction—multitasking and environmental noise—and this potentially limits its generalization to other contexts. In our work, we distinguish attention states based on a RTV analysis in gradCPT, depending less on distractions or other environmental factors.…”
While numerous studies have explored using various sensing techniques to measure attention states, moment-to-moment attention fluctuation measurement is unavailable. To bridge this gap, we applied a novel paradigm in psychology, the gradual-onset continuous performance task (gradCPT), to collect the ground truth of attention states. GradCPT allows for the precise labeling of attention fluctuation on an 800 ms time scale. We then developed a new technique for measuring continuous attention fluctuation, based on a machine learning approach that uses the spectral properties of EEG signals as the main features. We demonstrated that, even using a consumer grade EEG device, the detection accuracy of moment-to-moment attention fluctuations was 73.49%. Next, we empirically validated our technique in a video learning scenario and found that our technique match with the classification obtained through thought probes, with an average F1 score of 0.77. Our results suggest the effectiveness of using gradCPT as a ground truth labeling method and the feasibility of using consumer-grade EEG devices for continuous attention fluctuation detection.
“…Similarly, research concerning the association between divided attention and physiological parameters is rare. The only research work on investigating divided attention in correlation with EEG power bands was conducted by Rodrigue et al (2015). The study was aimed to determine the level of divided attention of users using the Emotiv EPOC device and concluded that the (black-box) algorithm implemented in this device was considered and deemed reliable.…”
Section: State Of the Art Of Physiological Approaches To Measuring Attentionmentioning
The affective state of an individual can be determined using physiological parameters; an important metric that can then be extracted is attention. Looking more closely at compact EEGs, algorithms have been implemented in such devices that can measure the attention and other affective states of the user. No information about these algorithms is available; are these feature classification algorithms accurate? An experiment was conducted with 23 subjects who utilized a pedagogical agent to learn the syntax of the programming language Java while having their attention measured by the NeuroSky MindWave Mobile 2. Using a concurrent validity approach, the attention values measured were compared to band powers, as well as measures of task performance. The results of the experiment were in part successful and supportive of the claim that the EEG device's attention algorithm does in fact represent a user's attention accurately. The results of the analysis based on raw data captured from the device were consistent with previous literature. Inconclusive results were obtained relating to task performance and attention.
“…Such a system could be used to manage educational content based on the level of attention the child keeps with the instructional material. A more robust technology-based approach is proposed by [15] to detect divided attention in reading activities. While children were reading the environment was fueled with distractors in the format of multitasking instructions or environmental noise.…”
Planning and conducting educational activities for children with ADHD represents a methodical and precise endeavor. Teachers plan the educational activities but also have to adapt each educational session based on the child's emotional state. Digital technologies are often suggested as a means to provide engaging learning resources and to help children with their academic achievements. Therefore, we developed a supportive software based on an educational activity where we aim to help children reinforce learning abilities. We conducted a controlled study to compare the manual and digital modalities of the educational activity. Our analysis reveals sentiment findings when new technology is introduced. Our findings suggest that using educational activities enhanced with digital technology has potential benefits and may allow teachers and children achieve academic goals yet providing a ludic educational experience for children.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.