Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Multi-Label EEG Dataset for Mental Attention State Classification in Online Learning

Huan Liu, Yuzhe Zhang, Guanjian Liu, Xinxin Du, Haochong Wang, Dalin Zhang

TL;DR

This work tackles the need for reliable EEG-based attention state assessment in online learning by introducing MEMA, a standardized multi-label EEG dataset with three attention states (neutral, relaxing, concentrating) collected from 20 subjects across 12 trials, totaling approximately 1,060 minutes. It provides comprehensive data collection, including emotion labels and Big Five personality traits, and validates data quality through qualitative EEG analyses and quantitative benchmarking for attention and emotion classification. The results show strong subject-dependent performance (up to 85.12%) and reasonable cross-subject generalization (up to 64.84%), and reveal meaningful links between attention and emotion, particularly valence and arousal, with opportunities for multi-task learning. MEMA thus offers a valuable resource for advancing attention monitoring in online learning and for exploring attention-emotion-personality interactions in EEG data.

Abstract

Attention is a vital cognitive process in the learning and memory environment, particularly in the context of online learning. Traditional methods for classifying attention states of online learners based on behavioral signals are prone to distortion, leading to increased interest in using electroencephalography (EEG) signals for authentic and accurate assessment. However, the field of attention state classification based on EEG signals in online learning faces challenges, including the scarcity of publicly available datasets, the lack of standardized data collection paradigms, and the requirement to consider the interplay between attention and other psychological states. In light of this, we present the Multi-label EEG dataset for classifying Mental Attention states (MEMA) in online learning. We meticulously designed a reliable and standard experimental paradigm with three attention states: neutral, relaxing, and concentrating, considering human physiological and psychological characteristics. This paradigm collected EEG signals from 20 subjects, each participating in 12 trials, resulting in 1,060 minutes of data. Emotional state labels, basic personal information, and personality traits were also collected to investigate the relationship between attention and other psychological states. Extensive quantitative and qualitative analysis, including a multi-label correlation study, validated the quality of the EEG attention data. The MEMA dataset and analysis provide valuable insights for advancing research on attention in online learning. The dataset is publicly available at \url{https://github.com/GuanjianLiu/MEMA}.

A Multi-Label EEG Dataset for Mental Attention State Classification in Online Learning

TL;DR

This work tackles the need for reliable EEG-based attention state assessment in online learning by introducing MEMA, a standardized multi-label EEG dataset with three attention states (neutral, relaxing, concentrating) collected from 20 subjects across 12 trials, totaling approximately 1,060 minutes. It provides comprehensive data collection, including emotion labels and Big Five personality traits, and validates data quality through qualitative EEG analyses and quantitative benchmarking for attention and emotion classification. The results show strong subject-dependent performance (up to 85.12%) and reasonable cross-subject generalization (up to 64.84%), and reveal meaningful links between attention and emotion, particularly valence and arousal, with opportunities for multi-task learning. MEMA thus offers a valuable resource for advancing attention monitoring in online learning and for exploring attention-emotion-personality interactions in EEG data.

Abstract

Attention is a vital cognitive process in the learning and memory environment, particularly in the context of online learning. Traditional methods for classifying attention states of online learners based on behavioral signals are prone to distortion, leading to increased interest in using electroencephalography (EEG) signals for authentic and accurate assessment. However, the field of attention state classification based on EEG signals in online learning faces challenges, including the scarcity of publicly available datasets, the lack of standardized data collection paradigms, and the requirement to consider the interplay between attention and other psychological states. In light of this, we present the Multi-label EEG dataset for classifying Mental Attention states (MEMA) in online learning. We meticulously designed a reliable and standard experimental paradigm with three attention states: neutral, relaxing, and concentrating, considering human physiological and psychological characteristics. This paradigm collected EEG signals from 20 subjects, each participating in 12 trials, resulting in 1,060 minutes of data. Emotional state labels, basic personal information, and personality traits were also collected to investigate the relationship between attention and other psychological states. Extensive quantitative and qualitative analysis, including a multi-label correlation study, validated the quality of the EEG attention data. The MEMA dataset and analysis provide valuable insights for advancing research on attention in online learning. The dataset is publicly available at \url{https://github.com/GuanjianLiu/MEMA}.

Paper Structure

This paper contains 15 sections, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Data Acquisition Paradigm
  3. Overall Collection Procedure
  4. Preparation before Recording
  5. Scene setting
  6. Individual information collection
  7. Task Design for Each Trail
  8. Technical Validation
  9. Dataset Description and Comparison
  10. Qualitative Analysis
  11. Quantitative Analysis
  12. Attention state classification
  13. Emotion classification
  14. Multi-label correlation study
  15. Conclusion

Figures (3)

  • Figure 1: Overall collection procedure consists of two parts: preparation before recording and EEG data recording.
  • Figure 2: Average power results (on topographical maps) and time-frequency of one subject.
  • Figure 3: The comparison of the accuracy of attention state classification in single-task and multi-task scenarios based on three base models with the subject-dependent setting and the cross-subject setting.