Guest Editorial: Intelligent and Affective Learning Environments: New Trends and Challenges.
Bibliographic record
Abstract
Technology poses a huge potential in the educational field (Stantchev et al., 2014). As a result of this, researchers in this field of study devote great part of their efforts on finding better technological solutions (Vasquez-Ramirez et al., 2014). Within this field, Traditional Intelligent Tutoring Systems (ITS) are able to support and control students' learning at several levels; however, it does not provide space for student-driven learning and knowledge acquisition. From this perspective, Intelligent Learning Environments and similar tutoring systems have emerged as a type of intelligent educational system that combines the features of traditional ITS with learning environments. This kind of educational system can be very helpful in supporting human learning by using Artificial Intelligence (AI) techniques, transforming information into knowledge, using it for tailoring many aspects of the educational process to the particular needs of each actor, and timely providing useful suggestions and recommendations (Brusilovsky et al., 1993; Carbonell, 1970; Clancey, 1979; Anderson et al., 1990; Aleven & Koedinger, 2002; Woolf, 2009). In addition to traditional cognitive state identification, ITS have recently incorporated the ability to recognize the emotions of students (Calvo & D'Mello, 2010; Wolf et al., 2009; Baker et al., 2010). These tutoring systems can detect the affective states of learners by using different types of data sources such as dialogs, speech, physiology, and facial expressions (Zeng et al., 2009; Calvo & D'Mello, 2010; Arroyo et al., 2009; Conati & Maclaren, 2009; Burleson, 2011). Moreover, they seek to transform negative states of students (e.g., confusion) into positive (e.g., commitment) in order to facilitate appropriate emotional conditions for learning. Affective Tutoring Systems identify confusion, frustration, boredom, engagement, and other prominent emotions during learning activities (D'Mello & Graesser, 2012; D'Mello et al., 2014; Graesser & D'Mello, 2012). The recognition of students' affective states can be implemented by different machine learning techniques, such as Bayesian Networks (Conati & Maclaren, 2009), Hidden-Markov Models (D'Mello & Graesser, 2010), or Neural Networks (Moridis & Economides, 2009). Although many works and studies have considered the development of affective tutoring systems, no research works have yet focused on Intelligent and Affective Learning Environments, where components involved in the environment (the learning environment, the intelligent tutoring system, and/or the adaptive system) support the learning process. Therefore, it is necessary to propose new approaches, techniques, methods, and processes in the field of Intelligent and Affective Learning Environments in order to consider cognitive and affective aspects in the teaching-learning and decision making processes. This special issue of Journal of Educational Technology & Society (ET&S) on Intelligent and Affective Learning Environments: New Trends and Challenges, contains one kind of contribution: regular research papers. These works have been edited according to the norms and guidelines of JETS. Several call for papers were distributed among the main mailing lists of the field for researchers to submit their works to this issue. In the first deadline, we received a total of 32 expressions of interest in the form of abstracts. Due to the large amount of submissions, abstracts were subject to a screening process to ensure their clarity, authenticity, and relevancy to this special issue. Proposals came from several countries such as Algeria, Bosnia and Herzegovina, Brazil, Canada, Colombia, Denmark, Germany, Greece, India, Ireland, the Republic of Korea, Malaysia, Malta, Mexico, New Zealand, Norway, Philippines, Poland, Romania, Serbia, Spain, Taiwan, Tunisia, Turkey, United Kingdom of Great Britain, Northern Ireland, and United States of America. …
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.015 |
| Meta-epidemiology (narrow) | 0.003 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.002 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.002 | 0.003 |
| Scholarly communication | 0.009 | 0.005 |
| Open science | 0.004 | 0.002 |
| Research integrity | 0.016 | 0.017 |
| Insufficient payload (model declined to judge) | 0.023 | 0.018 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".