No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
IDENTIFYING STUDENT EMOTIONS IN AN ADAPTIVE LEARNING SYSTEM WITH A BAYESIAN NETWORK MODEL
Abstract
The assessment of affective states in online learning often relies on various devices, such as sensors, which indicate physiological reactions of a person's emotional state. It is important to note that not every university can afford the sensors and devices required for this purpose. Furthermore, not every student may be willing to monitor their emotional state using sensors on a personal computer during online learning. This article focuses on the potential benefits of detecting affective states through self-reported survey responses. It aims to explore ways to improve student‘s learning by identifying and responding to specific emotional states during online learning. This paper presents the identification of emotions using a survey, administered to engineering students during an e-learning course in the adaptive
learning system (ALS). In addition, the authors developed a model of Bayesian Network (BN) to analyze the current emotional state of students in e-learning and propose supportive messages to students in order to improve their emotional state.
ResearchGate has not been able to resolve any citations for this publication.
Predicting student performance is crucial in higher education, as it facilitates course selection and the development of appropriate future study plans. The process of supporting the instructors and supervisors in monitoring students in order to upkeep them and combine training programs to get the best outcomes. It decreases the official warning signs and inefficient students' expulsions. Therefore, analysis of students' performance on various academic tests is critical for future skill development. Despite the fact that existing performance prediction systems based on Deep Learning (DL) technologies such as Artificial Neural Networks (ANN), Recurrent Neural Network (RNN) have outperformed Machine Learning (ML) -based systems in the prediction task, there are still a few issues. Ignorance of relevant features, analysis limitations to the existing amount of data points, and ambiguity in student records are only a few of these issues. This research proposes a novel Student Academic Performance Predicting (SAPP) system to address these issues and enhance prediction accuracy. It has a better architecture that uses a combination of 4-layer stacked Long Short Term Memory (LSTM) network, Random Forest (RF), and Gradient Boosting (GB) techniques to predict students' pass or fail outcomes. Additionally, the proposed SAPP system is compared to existing prediction systems using publicly accessible student OULAD dataset with an addition of self-curated emotional dataset. The performance of SAPP system is measured using Accuracy, Precision, F-measure, and Recall parameters. The results of proposed algorithm (LSTM + RF + B) is compared with LSTM + RF, LSTM + B and end to end DL models such as ANN, LSTM, RNN, Convolutional Neural Network (CNN) and most commonly utilized ML models in the literature such as Support Vector Machine (SVM), Decision Tree (DT), Naive Bayes (NB) and RF. The proposed SAPP system gained approximately 96% prediction accuracy that is comparatively higher than existing systems.
Positive and negative activation (PA/NA) represent two general activation systems of affect that are of importance for studying personality. Hereby, many studies focus on state assessment of PA and NA in everyday situations, using the ‘Experience Sampling Method’ (ESM) performed via mobile devices. ESM studies require short, reliable and validated non-verbal scales for immediate and fast capturing of personality and situation characteristics. In this study we present the non-verbal ‘Lebender Emoticon PANAVA’ scale (LE-PANAVA), consisting of five items capturing PA, NA, and valence (VA). LE-PANAVA is based on the 10-item verbal PANAVA-KS scale developed by Schallberger (2005). The development of LE-PANAVA consisted of a three step process: The graphical development and selection of a set of emoticons (study 1), the validation of the set of emoticons and corresponding adjustments to the scale (study 2), and validation of the final scale (study 3). We conclude from the results that LE-PANAVA captures the two factors PA and NA, but are aware that they are closely interrelated. Additional to LE-PANAVA, an ultra-short version was derived, that is, a forced choice 2 × 2 matrix of emoticons – the ‘Lebender Emoticon PANA Matrix’ (LE-PANA-M). Both LE-PANAVA and LE-PANA-M are available for future research and practical application.
Automated emotion recognition (AEE) is an important issue in various fields of activities which use human emotional reactions as a signal for marketing, technical equipment, or human–robot interaction. This paper analyzes scientific research and technical papers for sensor use analysis, among various methods implemented or researched. This paper covers a few classes of sensors, using contactless methods as well as contact and skin-penetrating electrodes for human emotion detection and the measurement of their intensity. The results of the analysis performed in this paper present applicable methods for each type of emotion and their intensity and propose their classification. The classification of emotion sensors is presented to reveal area of application and expected outcomes from each method, as well as their limitations. This paper should be relevant for researchers using human emotion evaluation and analysis, when there is a need to choose a proper method for their purposes or to find alternative decisions. Based on the analyzed human emotion recognition sensors and methods, we developed some practical applications for humanizing the Internet of Things (IoT) and affective computing systems.
Emotions play an important role in the learning process. Considering the learner's emotions is essential for electronic learning (e-learning) systems. Some researchers have proposed that system should induce and conduct the learner's emotions to the suitable state. But, at first, the learner's emotions have to be recognized by the system. There are different methods in the context of human emotions recognition. The emotions can be recognized by asking from the user, tracking implicit parameters, voice recognition, facial expression recognition, vital signals and gesture recognition. Moreover, hybrid methods have been also proposed which use two or more of these methods through fusing multi-modal emotional cues. In the e-learning systems, the system’s user is the learner. For some reasons, which have been discussed in this study, some of the user emotions recognition methods are more suitable in the e-learning systems and some of them are inappropriate. In this work, different emotion theories are reviewed. Then, various emotions recognition methods have been represented and their advantages and disadvantages of them have been discussed for utilizing in the e-learning systems. According to the findings of this research, the multi-modal emotion recognition systems through information fusion as facial expressions, body gestures and user’s messages provide better efficiency than the single-modal ones.
Recently, a growing body of literature has shown the importance of emotions in e-learning processes by pointing out their effect on academic achievement. Nevertheless, within innovative teaching models, the affective-behavioral notion of engagement has been neglected. The aim of the present pilot study is to analyse the experienced emotions by students within different e-learning contexts (chats with teacher, private group discussions, forum threads and content activities) and understand their possible relation with students' engagement. Our results point out that when e-learners experience positive emotions across synchronous learning activities (chats with teachers and among students) the engagement dimensions of affective relevance and participation significantly increase. Further, we found that negative emotions play a central role during the interactive activities with teacher, as performing these learning tasks can be a first warning of an insufficient preparation. Therefore the study demonstrates the importance for an for citations: Journal of e-Learning and Knowledge Society Je-LKS Je-LKS e-teacher to regulate students' negative emotions experienced across the e-learning activities, as they can negatively influence both affective and behavioural dimensions of engagement.
In this work we investigate the importance of emotion awareness in e-learning environments, with emphasis to Computer Supported Collaborative Learning (CSCL) activities. Our presented solution involves a new conceptual model of emotions of interest in e-learning context. In the basis of this model, a computational model has been implemented employing self-report of emotions, affective feedback and effective emotion visualisations. Both models have been tested in real education settings, contributing to the research agenda.
To improve the quality of e-learning and overcome the limitations of the current
online educational environments, we propose to take into consideration the emotional states
of students during e-learning sessions. Thus, we present architecture of emotionally
intelligent e-learning system based on a computational probabilistic model of emotions and
ensuring two abilities of emotional intelligence: emotion recognition and emotion induction.
This paper describes a system's implementation that evaluates the learner's affective state and based on computer intelligence, responds affectively. Prominent theories and models of emotions are reviewed and analysed, especially in respect to learning, together with emotion recognition technologies. Finally, we set open issues for future experimentation, contributing to the research agenda.
Aside from test anxiety scales, measurement instruments assessing students’ achievement emotions are largely lacking. This article reports on the construction, reliability, internal validity, and external validity of the Achievement Emotions Questionnaire (AEQ) which is designed to assess various achievement emotions experienced by students in academic settings. The instrument contains 24 scales measuring enjoyment, hope, pride, relief, anger, anxiety, shame, hopelessness, and boredom during class, while studying, and when taking tests and exams. Scale construction used a rational–empirical strategy based on Pekrun’s (2006) control-value theory of achievement emotions and prior exploratory research. The instrument was tested in a study using a sample of university students (N = 389). Findings indicate that the scales are reliable, internally valid as demonstrated by confirmatory factor analysis, and externally valid in terms of relationships with students’ control-value appraisals, learning, and academic performance. The results provide further support for the control-value theory and help to elucidate the structure and role of emotions in educational settings. Directions for future research and implications for educational practice are discussed.Research highlights► First comprehensive instrument measuring students’ multiple achievement emotions. ► Findings corroborate Pekrun’s control-value theory of achievement emotions. ► Need to differentiate between various discrete emotions. ► Achievement emotions linked to motivation, strategies, self-regulation, performance.
Affective or Emotion oriented computing constitutes an emerging research field that is still in its early stages. The lack of empirical results together with the complexity that attributes emotions, subjects research to a diversity of theories, models and tools. In the current paper we present a critical review of the state of the art on emotion measurement models, methods and tools and we suggest some informal rules towards their realistic use in education settings.
The consideration of emotion in learning has been in the research agenda for quite long time and literature is offering a variety of studies that are evaluating the role of emotions in various learning contexts (class, test and exams, during studying at home, etc). In the current paper we first appose a critical review of prominent emotion taxonomies, affect detection and feedback strategies and then we propose the design of a system that is endowed with students' emotion aware capabilities. An emotion taxonomy that originates from the basic emotions of fear and affection is put forward. Social-Emotional Learning Theory and Practice can be exploited to feed the necessary theoretical background that is lacking of empirical data.
To date, little research has been done on the role of emotions with respect to computer related behaviours. The purpose of this study was to develop a reliable, valid scale to assess emotions while learning with computers. Four emotions (anger, anxiety, happiness, and sadness), selected after a detailed review of the research, were evaluated. Internally reliability estimates were acceptable. Construct validity was confirmed by an exploratory factor analysis. Convergent validity was supported by strong correlations among emotions and affective attitude, but not cognitive and behavioural attitudes. Finally, predictive validity was corroborated by consistent and significant correlations among emotion, computer knowledge, and use.
Using emotion detection technologies from biophysical signals, this study explored how emotion evolves during learning process and how emotion feedback could be used to improve learning experiences. This article also described a cutting-edge pervasive e-Learning platform used in a Shanghai online college and proposed an affective e-Learning model, which combined learners' emotions with the Shanghai e-Learning platform. The study was guided by Russell's circumplex model of affect and Kort's learning spiral model. The results about emotion recognition from physiological signals achieved a best-case accuracy (86.3%) for four types of learning emotions. And results from emotion revolution study showed that engagement and confusion were the most important and frequently occurred emotions in learning, which is consistent with the findings from AutoTutor project. No evidence from this study validated Kort's learning spiral model. An experimental prototype of the affective e-Learning model was built to help improve students' learning experience by customizing learning material delivery based on students' emotional state. Experiments indicated the superiority of emotion aware over non-emotion-aware with a performance increase of 91%.
The aim of this paper is to describe the evaluation process and findings of an AI-based Adaptive Learning System for the Computer Science discipline at two different German universities and discuss an array of methods in regard to assessing such a system. The primary objectives have been twofold: firstly, to examine the reception of selected learning elements, which were conceptually outlined based on relevant literature, among the student body; and secondly, to investigate the efficacy of individualized adaptive learning paths. These paths were generated by employing a variety of algorithms to analyze students learning style tendencies, with a particular emphasis on adaptive navigational techniques. The used algorithms encompassed a modified version of a literature based adaptive mechanism, an Ant-Colony-Algorithm and a Genetic Algorithm, alongside a lecturer-recommended learning path for a non-adaptive comparison. While the system suggested suitable learning paths based on student data, it never forced the individuals to give up their self-directed learning. The evaluation criteria revolved around the evolution of student motivation, interest levels, and knowledge acquisition during the time they spent working in the system. The evaluation sought to facilitate comparative analyses and assess algorithmic fitness for proficient learning path generation. The methods included both quantitative and qualitative approaches to gather data, seeking to strike a balance between being student-friendly and scientifically informative. They ranged from Likert Scale self-assessments to screen and video observations with retrospective interviews. Since the purpose of adaptive learning systems is intertwined with personalized learning it seems imperative to already take the preferences and opinions of students into account while the system is still in development. This complexity underscores the challenge of evaluating such systems, as significant constraints on student choice - though simplifying evaluation - directly oppose the ethos of individualized, self-directed learning. Initial findings suggest that the underlying theoretical considerations on sequencing and structuring of learning elements are confirmed, coupled with providing adequate flexibility to meet diverse learning needs. Cross-site evaluation of the literature-based learning elements indicated a high comprehensibility and positive student ratings. While significant positive trends were observed regarding knowledge acquisition, they cannot be definitively attributed to a specific method of learning path generation. Motivation and interest analyses show no significant differences among learning path types, albeit heavily limited by sample size. Similarly, emotion measurements, though limited, hint at positive impacts from HASKI system use. Despite limitations, early indications suggest student acceptance and potential effectiveness of learning paths, highlighting the need for larger sample sizes for validation and expansion. Ensuring alignment with student needs and user-friendly design are crucial considerations.
This special issue of Learning and Instruction examines the role of emotions in academic learning, with a special focus on emotions in computer-supported academic learning (or e-learning). Three central research challenges concerning emotion in e-learning are: identification (e.g., what are the key emotions in e-learning?), measurement (e.g., how can we tell how strongly a learner is experiencing each key emotion during e-learning?), and explanation (e.g., what are the causes and consequences of the learner's emotional state during learning?). A useful goal of research on emotions in e-learning is to test an affective-cognitive model of e-learning with links among an e-learning episode, the learner's emotional reaction during learning, the learner's cognitive processing during learning, and the learning outcome.
E-learning provides an unprecedented flexibility and convenience for e-learners by breaking the limitations of space and time. However, the role of emotion is neglected in current e-learning systems. We focus strictly on negative emotions of e-learners, integrating emotion regulation theories with recommender technique, and present the study of learner-oriented negative emotion compensation in this paper. Inspiring from the existing emotion regulation model in the field of psychology, we design the architecture of learner-oriented negative emotion compensation in e-learning. Finding e-learner's personalized emotion regulation strategies and methods from questionnaires, we propose an approach of e-learner's negative emotion compensation based on recommender users and music. In practice, the usability of emotion compensation is verified by an e-learning platform, as a complementary demonstration, the learner satisfaction is done by a 90-e-learner survey in real elearning. The results show that the proposed learner-oriented negative emotion compensation provides greater satisfaction for the e-learner, and is a feasible and effective method for e-learner to decrease negative emotions in e-learning.
Emotions are ubiquitous in academic settings, and they profoundly affect students’ academic engagement and performance. In this chapter, we summarize the extant research on academic emotions and their linkages with students’ engagement. First, we outline relevant concepts of academic emotion, including mood as well as achievement, epistemic, topic, and social emotions. Second, we discuss the impact of these emotions on students’ cognitive, motivational, behavioral, cognitive-behavioral, and social-behavioral engagement and on their academic performance. Next, we examine the origins of students’ academic emotions in terms of individual and contextual variables. Finally, we highlight the complexity of students’ emotions, focusing on reciprocal causation as well as regulation and treatment of these emotions. In conclusion, we discuss directions for future research, with a special emphasis on the need for educational intervention research targeting emotions.
This article reports about the development and validation of a measurement instrument assessing elementary school students' achievement emotions (Achievement Emotions Questionnaire-Elementary School, AEQ-ES). Specifically, the instrument assesses students' enjoyment, anxiety, and boredom pertaining to three types of academic settings (i.e., attending class, doing homework, and taking tests and exams). Scale construction was based on Pekrun's (2006) control-value theory of achievement emotions. The instrument was tested using samples from German and American elementary school classrooms. The results of Study 1 (German sample) corroborate the reliability and structural validity of the new emotion measure. Moreover, they show that students' achievement emotions were linked with their control and value appraisals as well as their academic performance, thus supporting the external validity of the measure as well as propositions of Pekrun's (2006) control-value theory of achievement emotions. Study 2 (American sample) corroborated the cross-cultural equivalence of the measure and the generalizability of findings across the German and American samples. Implications for research on achievement emotions and educational practice are discussed.
Motivational techniques and strategies that may be used by teachers to strengthen student performance and reinforce positive attitudes toward learning are discussed and analyzed. The topic is divided into eight major factors for consideration: (1) why human behavior occurs, what is motivation, the mythology of motivation and learning, and the time continuum model of motivation; (2) perceptions and judgments that influence action, and student attitudes; (3) physiological and psychological needs; (4) connection of learning activities, variety, interest, and involvement; (5) humanizing education; (6) competence, awareness of progress and mastery, responsibility, and competition; (7) positive reinforcement; and (8) inventory of motivation strategies, basic motivation planning, and final comments. Case studies and examples of teacher-pupil interchanges are included in the discussion of each topic. (JD)
Emotions are ubiquitous in achievement settings. Apart from test anxiety research and attributional studies, psychological research has neglected these emotions. We argue that more research on the functions, origins, and regulation of achievement emotions is needed, addressing both outcome emotions related to success and failure, such as hope, pride, anxiety, shame, and hopelessness, and activity emotions such as the enjoyment and boredom experienced in achievement settings. Using Pekrun’s (2006) control-value theory of achievement emotions as a theoretical framework, we first outline a three-dimensional (object focus × valence × activation) taxonomy of achievement emotions. We then summarize research on the individual and social origins of these emotions, arguing that control appraisals, value appraisals, achievement goals, and related contextual factors are of specific relevance for achievement emotion arousal. Next, the importance of emotions for achievement behavior and performance is addressed. In conclusion, we discuss the regulation and modification of achievement emotions and their relative universality across genders, settings, and cultures.
We describe a method for sensitivity communication robots which infer their dialogist's emotion. The method is based on the Bayesian approach: by using a Bayesian modeling for prosodic features. In this research, we focus the elements of emotion included in dialogist's voice. Thus, as training datasets for learning Bayesian networks, we extract prosodic feature quantities from emotionally expressive voice data. Our method learns the dependence and its strength between dialogist's utterance and his emotion, by building Bayesian networks. Bayesian information criterion, one of the information theoretical model selection method, is used in the building Bayesian networks. The paper finally proposes a reasoner to infer dialogist's emotion by using a Bayesian network for prosodic features of the dialogist's voice. The paper also reports some empirical reasoning performance.
Trait emotional intelligence refers to a constellation of emotional self-perceptions located at the lower levels of personality hierarchies. In 2 studies, we sought to examine the psychometric properties of the Trait Emotional Intelligence Questionnaire-Short Form (TEIQue-SF; Petrides, 2009) using item response theory (IRT). Study 1 (N= 1,119, 455 men) showed that most items had good discrimination and threshold parameters and high item information values. At the global level, the TEIQue-SF showed very good precision across most of the latent trait range. Study 2 (N= 866, 432 men) used similar IRT techniques in a new sample based on the latest version of the TEIQue-SF (version 1.50). Results replicated Study 1, with the instrument showing good psychometric properties at the item and global level. Overall, the 2 studies suggest the TEIQue-SF can be recommended when a rapid assessment of trait emotional intelligence is required.
The control-value theory of achievement emotions: Assumptions, corollaries, and implications for educational research and practice
- R Pekrun
R. Pekrun, "The control-value theory of achievement emotions: Assumptions, corollaries, and
implications for educational research and practice," Educational psychology review, vol. 18, pp.
315-341., 2006. DOI 10.1007/s10648-006-9029-9.
Towards unobtrusive emotion recognition for affective social communication
- H Lee
- Y S Choi
- I P Park
H. Lee, Y. S. Choi, I.P. Park, "Towards unobtrusive emotion recognition for affective social
communication," 2012 IEEE Consumer Communications and Networking Conference (CCNC).
IEEE, pp. 260-264, 2012.
A three-dimensional taxonomy of achievement emotions
- R Pekrun
- H W Marsh
- A J Elliot
- K Stockinger
- R P Perry
- E Vogl
- T Goetz
- W Van Tilburg
- O Lüdtke
- W P Vispoel
R. Pekrun, H. W. Marsh, A. J. Elliot, K. Stockinger, R. P. Perry, E. Vogl, T. Goetz, W. AP Van
Tilburg, O. Lüdtke, W. P. Vispoel, "A three-dimensional taxonomy of achievement emotions,"
Journal of Personality and Social Psychology, vol. 124, no. 1, p. 145, 2023.
https://doi.org/10.1037/pspp0000448.supp.