Measuring Students Affective States through Online Learning Logs — An Application of Learning Analytics

Abstract

The affective state is determinate to online learning quality. It is related to students' attitude, learning motivation, and learning engagement. Learning affective states consists of engagement, frustration, confusion, and off-task state in this study. Different affective states are associated with different online learning behavior features. Affective states analysis consists of data collecting, data processing, affective states analyzing, evaluating, and intervening. Students' affective states can be analyzed by the affective state detectors. 12,912 online learning operations from an online course are used to construct the affective state detectors and examine the effectiveness. The consistency of the analysis results with the self-reports supported that the model is reliable to analyze students' affective state.Index Terms-Research and application, online affective state; analysis model.

Predicting the Persuasiveness of Influence Strategies From Student Online Learning Behaviour Using Machine Learning Methods

“…For instance, Đurđević Babić (2015) reported that neural network model with an accuracy score of 73.33% is the best model for predicting students’ satisfaction in a course using their learning data. Wang et al (2019) revealed that students’ learning affective states such as concentration, frustration, confusion, and off-task could be predicted from their learning data with F-scores of 57%, 74%, 44%, and 75% respectively using Nave Bayes and K* algorithms. Moreover, Park et al (2016) applied multimodal models and predicted the persuasiveness of communication modalities on social multimedia with a mean accuracy score of 70.34%.…”

“…The neural network model known as the multilayer perceptron achieved the best overall classification accuracy with an average of 73.33%. Moreover, a study showed that learning log data of students could be utilized to build models for detecting various learning affective states (such as engagement, frustration, confusion, and off-task) of students (Wang et al, 2019). The study results indicated that the correlation between affective state analysis and self-report was 83.6%, demonstrating the validity of the data analysis model.…”

Automatic modeling of student characteristics with interaction and physiological data using machine learning: A review

“…The term “affective states of students in learning” has been used to denote a range of variables related to their motivation, engagement, and attitude. For example, in Wang et al ( 2019 ), the affective states comprise confusion, engagement, off-task, and frustration. According to Shute and Zapata-Rivera ( 2012 ), the affective states consist of motivated, attentive, engaged, and frustrated.…”

“…Detecting positive and negative affective states of students is important in improving and supporting their learning processes and progress. According to research, learning affective states include students' concentration, confusion, frustration and off-task behaviors (Wang et al, 2019 ). A number of studies conducted in the area of affective computing in education have recognized the role of affective states especially the learning affective states in facilitating learning activities (Wiggins et al, 2015 ; Jiménez et al, 2018 ; Standen et al, 2020 ).…”

“…Affective states Recurrent neural network, logistic regression, random forest, and K* Ranges from 70 to 85% Botelho et al, 2017;DeFalco et al, 2018;Salmeron-Majadas et al, 2018;Ghaleb et al, 2019;Hutt et al, 2019;Khan et al, 2019;Wang et al, 2019Engagement Edmond Meku Fotso et al, 2020Erkan et al, 2020;Raj and Renumol, 2022 Recurrent neural network and random forest Ranges from 80 to 95%…”