The individualization of the learning process is widely seen as a key promise for adaptive technology, such as artificial intelligence (AI). In an environment that provides individualized learning, the system recognizes the current states of learners and adjusts the environment accordingly. Most commonly, the focus in such systems is on cognitive variables. For example, an AI in a learning management system (LMS) may provide a learner with a learning path, tailored to their current level of knowledge or skill.
However, the individual learning process is shaped by additional - and often less stable - metacognitive, motivational, and affective factors. Thus, adaptive systems that truly support individualized learning require technology for the recognition of and reaction to all factors involved, as well as to consider their complex interrelations.
The goal of this Research Topic is to take a comprehensive view of the topic, by pooling recent research on adaptive technology for individualized learning, that can include but goes beyond cognitive learner variables. In particular, the aim is to collect research considering metacognitive, motivational, and affective variables on one or more of the three following levels:
1. Recognition and measurement
Because metacognitive, motivational, and affective variables can be transient within relatively short periods of time, innovative recognition and measurement are required. Related issues concern, among others, temporal resolution, unobtrusiveness, and psychometric properties of such measures.
2. Adaptivity
Adaptivity involves adjustments of the system to incorporate information on metacognitive, motivational, and affective variables. Related issues concern what to adapt, the dynamic or frequency of adaptation (macro to micro level), and the targeted learner variables.
3. System evaluation
Assessing whether an adaptive system is effective in supporting individualized learning is an open challenge. Related issues concern the definition of criteria for effectiveness, type of assessment, or considering corollaries of learning with adaptive technology (e.g., acceptance/user experience and system transparency).
This Topic welcomes original research, empirical studies, brief research reports, systematic reviews, mini-reviews, and conceptual analyses. Contributions may address cognitive learner variables (e.g., prior knowledge) provided this is done within the scope of metacognitive, motivational, and/or affective variables. Topics for this collection include, but are not limited to:
- Dynamic measurement of metacognitive, motivational, and/or affective learner variables (e.g., self-regulatory skill assessment, emotion recognition)
- Dynamic adjustments based on metacognitive, motivational, and/or affective learner variables (e.g., prompts, scaffolds, adjusting learning paths)
- Whole system evaluations that:
o address cognitive variables as outcomes in systems that adapt to metacognitive, motivational, and/or affective learner variables
o address metacognitive, motivational, and/or affective variables as outcomes or corollaries of learning with adaptive technology
- Game-based learning, serious games, applied games
- Learning management systems (LMS)
- Tutoring systems
- Ubiquitous learning applications
The individualization of the learning process is widely seen as a key promise for adaptive technology, such as artificial intelligence (AI). In an environment that provides individualized learning, the system recognizes the current states of learners and adjusts the environment accordingly. Most commonly, the focus in such systems is on cognitive variables. For example, an AI in a learning management system (LMS) may provide a learner with a learning path, tailored to their current level of knowledge or skill.
However, the individual learning process is shaped by additional - and often less stable - metacognitive, motivational, and affective factors. Thus, adaptive systems that truly support individualized learning require technology for the recognition of and reaction to all factors involved, as well as to consider their complex interrelations.
The goal of this Research Topic is to take a comprehensive view of the topic, by pooling recent research on adaptive technology for individualized learning, that can include but goes beyond cognitive learner variables. In particular, the aim is to collect research considering metacognitive, motivational, and affective variables on one or more of the three following levels:
1. Recognition and measurement
Because metacognitive, motivational, and affective variables can be transient within relatively short periods of time, innovative recognition and measurement are required. Related issues concern, among others, temporal resolution, unobtrusiveness, and psychometric properties of such measures.
2. Adaptivity
Adaptivity involves adjustments of the system to incorporate information on metacognitive, motivational, and affective variables. Related issues concern what to adapt, the dynamic or frequency of adaptation (macro to micro level), and the targeted learner variables.
3. System evaluation
Assessing whether an adaptive system is effective in supporting individualized learning is an open challenge. Related issues concern the definition of criteria for effectiveness, type of assessment, or considering corollaries of learning with adaptive technology (e.g., acceptance/user experience and system transparency).
This Topic welcomes original research, empirical studies, brief research reports, systematic reviews, mini-reviews, and conceptual analyses. Contributions may address cognitive learner variables (e.g., prior knowledge) provided this is done within the scope of metacognitive, motivational, and/or affective variables. Topics for this collection include, but are not limited to:
- Dynamic measurement of metacognitive, motivational, and/or affective learner variables (e.g., self-regulatory skill assessment, emotion recognition)
- Dynamic adjustments based on metacognitive, motivational, and/or affective learner variables (e.g., prompts, scaffolds, adjusting learning paths)
- Whole system evaluations that:
o address cognitive variables as outcomes in systems that adapt to metacognitive, motivational, and/or affective learner variables
o address metacognitive, motivational, and/or affective variables as outcomes or corollaries of learning with adaptive technology
- Game-based learning, serious games, applied games
- Learning management systems (LMS)
- Tutoring systems
- Ubiquitous learning applications