Search

The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link. This research aims to identify a feasible model to predict a learner’s stress in an online learning platform. It is desirable to produce a cost-effective, unobtrusive and objective method to measure a learner’s emotions. The few signals produced by mouse and keyboard could enable such solution to measure real world individual’s affective states. It is also important to ensure that the measurement can be applied regardless the type of task carried out by the user. This preliminary research proposes a stress classification method using mouse and keystroke dynamics to classify the stress levels of 190 university students when performing three different e-learning activities. The results show that the stress measurement based on mouse and keystroke dynamics is consistent with the stress measurement according to the changes of duration spent between two consecutive questions. The feedforward back-propagation neural network achieves the best performance in the classification.

Mass production of individualized products becomes essential for delivering personalized customer experience in the Industrial Revolution 4.0 era. Developing seamless value chain integration between enterprises, such as suppliers, retailers, and manufacturers, to achieve mass production of individualized products is challenging. This paper proposes a method of asset integration and asset data channeling between enterprises in a value chain, namely Asset Administration System (AAdSys), designed based on RAMI 4.0. A use case that involves PEC application and OMIS manufacturing line for full automation of individualized mixed juice production is developed. The use case demonstrates how data channeling between a retailer and a manufacturer using AAdSys can be done.

Learner centred design (LCD) focuses on creating an e-learning system that can fulfil individual needs through personalization, nevertheless there are still many technical challenges. Besides, losing balanced focus on both of the learners and the instructors does not help to create a successful e-learning system. User-centred design helps to improve the usability of a system as it integrates requirements and user interface designs based on users’ needs. The findings of this research prove that even the users are provided with the same LMS, not everyone has the same perceptions or tolerance levels of the seven design factors that may cause frustrations to the users, and not everyone has the same satisfaction level of navigation experience and interface design. It is important for the LMS developers to understand that the variations between roles, genders, experiences and ages exist and should not be ignored when designing the system. KEYWORDS Learning Management System, Socio-demographics Differences, User-centred Design, User Interface Design, User Satisfactions

Over the past decades, research in affective learning has begun to take emotions into account, which advocates an education system that is sentient of learner’s cognitive and affective states, as learners’ performance could be affected by emotional factors. This exploratory research examines the impacts of mental arithmetic demand and external stimuli on learner’s stress perception and job performance. External stimuli include time pressure and displays of countdown timer and clock on an online assessment system. Experiments are conducted on five different groups of undergraduate students, with a total of 160 of them from a higher learning institution. The results show that the impacts are significant. Correlations between task demand, external stimuli, learner’s stress and job performance are also significant.

Learner centred design (LCD)focuses on creating an e-learning system that can fulfil individual needs through personalization, nevertheless ther e are still many technical challenges. Besides, losing balanced focus on both of the learners and the instructorsdoes not help to create a successfule-learning system. User-centred design helps to improve the usability of a system as it integrates requirements and user interface designs based on users’ needs. The findings of this research prove that even the users are provided with the same LMS, not everyone has the same perception s or tolerance levels of the seven design factors that may cause frustrations to the users, and not everyone has the same satisfaction level of navigation experience and interface design.It is important for the LMS developers to understand that the variations between roles, genders, experiences and ages exist and should not be i gnored when designing the system.

A modern Intelligent Tutoring System (ITS) should be sentient of learner's cognitive and affective states, as learner's performance could be affected by motivational and emotional factors. It is important to design a low-cost and unobtrusive computational method for ITS to determine learner's states automatically. The automated learner's data sensing is useful in the development of personalized e-learning that can adapt learning content according to individual's emotion. Although many past findings relate stressor such as task demand to learner's emotion, however there is a lack of existing studies that examine the impact of stressor on learners' cognitive states and their mouse and keystroke dynamics. This exploratory research, conducted on 160 undergraduate students, found that the impacts of direct learning instruction and external stress stimuli, such as timer display, on learner's cognitive and affective states are significant. The correlations between direct instruction, external stimuli, learners' cognitive and affective states, as well as their mouse and keystroke behaviours are also significant.

This paper presents the application of Motivation/Attitude-driven Behavior (MADB) model proposed by Wang (Wang, 2007a) in the e-learning context. The authors' work demonstrates how mathematical models and formal cognitive processes is developed based on menu search task. The effects of menu design on stress perceptions, motivation and attitudes during the search tasks are being examined. The correlations between emotion (stress perception), motivation, attitude, decision, behavior and mouse behavior are studied. The authors' findings are consistent with what was proposed by Wang. They also found that behavior is significantly correlated to mouse dynamics, such as mouse speed, mouse idle duration and mouse left click rate. Generally strong behavior strength results in slower mouse movements. The significant effect of behavior on mouse dynamics may be caused by motivation and decision, but not attitude and stress perception.

To build a personalized e-learning system that can deliver adaptive learning content based on student’s cognitive effort and efficiency, it is important to develop a construct that can help measuring perceived mental state, such as stress and cognitive load. The construct must be able to be quantified, computerized and automated. Our research investigates how mouse and keyboard dynamics analyses could be used to detect cognitive stress, which is induced by high mental arithmetic demand with time pressure, without using intrusive and expensive equipment. The research findings suggest that when task demand increased, task error, task duration, passive attempt, stress perception and mouse idle duration may increase, while mouse speed, left mouse click and keystroke speed decreased. The significant effects of task demand and time pressure on mouse and keystroke behaviours suggest that stress evaluation from these input devices is potentially useful for designing an adaptive e-learning system.

Past research found that cognitive effort is related to emotion, which negative emotion may influence task performance. To enhance learning experience, it is important to have an effective technique to measure user’s emotional and motivational affects for designing an adaptive e-learning system, rather than using a subjective method that is less reliable and accurate. Keystroke and mouse dynamics analyses shed light on a better automated emotion recognition method as compared to physiological methods, as they are cheaper, non-invasive and can be easily set up. This research shows that unification of mouse and keyboard dynamics analyses could be useful in detecting emotional stress, particularly stress induced by time pressure, text length and language familiarity. The changes of mouse and keystroke behaviours of the students are found cohere with their task performance and stress perception. However anomalies in mouse and keystroke behaviours present when the students are pushed beyond their capabilities.

Automated stress detection is important in developing adaptive e-learning systems. Empirical evidence suggests that mouse dynamics and keyboard dynamics analyses can be both effective in user behaviour modelling as well as emotion detection compared to physiological measures and facial expression recognitions, and yet they are far less expensive and considered non-intrusive. This paper investigates how mouse dynamics and keyboard dynamics can be affected by emotional stress, particularly stress induced by time pressure, text length and language familiarity. Our research findings show that longer text and unfamiliar language raise users’ stress perceptions. Demanding job such as long typing task could result in anomalous behaviours once the users have lost motivation. Language familiarity mainly affects keyboard behaviour but text length change mouse behaviour. This shows that there is a good potential of developing an adaptive e-learning system by detecting learners’ emotional stress from keyboard and mouse input.

Much research has been done to detect human emotion using various computational methods, such as physiological measures and facial expression recognition. These methods are effective but they could be expensive or intrusive as special setups of equipment are needed. Some researchers have utilized nonintrusive methods by using mouse or keyboard analyses and presented comparable effectiveness in detecting human emotion. This paper investigates how both keyboard and mouse features can be combined to detect human stress, particularly cognitive stress induced by time pressure and mental arithmetic problems. The results show that the complexity of the mental arithmetic problem and time pressure affect user behaviour, mouse behaviour and keyboard behaviour significantly. This indicates that automatic analysis of human stress from keyboard and mouse input is potentially useful for providing adaptation in interactive systems such as an e-learning system.