Does gender stereotype threat affects the levels of aggressiveness, learning and flow in gamified learning environments?: An experimental study.

Studies in the literature reported several positive benefits provided by the use of technology in online education, especially in the gamified tutoring system. However, despite the benefits of intelligent tutoring systems, recent studies indicate the presence of a gender gap not considered in the construction of the attributes present in the gamified tutoring system. To investigate this impact by observing users' behavioral changes in gamified online educational environments, the present study aims to investigate the effects of the stereotype threats using a quantitative experiment with a Factorial Design in three gamified environments (stereotypical male version, stereotypical female version and control environment). Was conducted an experiment with 150 individuals (high school and undergraduate students) without considering age, ethnicity, or social class. The results show that the participants allocated to the male learning environment present an increase in aggressiveness level. Furthermore, the results also show the stereotypical male and female learning environments increased the participants' performance level. Another finding was that the threatening condition provided a significant increase in the participants' flow level among males subjected to a threatening condition, which did not manifest in the case of females. In addition, this study also observed the effect of the stereotype threat on men and women in the threatening condition by division in the 34-year age group, resulting in a significant increase in the level of flow among men. This study showed previous results show that the gamified environment influences psychological variables as aggressiveness, intellectual performance, and flow level, they raise questions about the direction of these changes and the impact they may have on users' usability and performance in these systems.

Exploring Kid Space in the wild: a preliminary study of multimodal and immersive collaborative play-based learning experiences.

Parents recognize the potential benefits of technology for their young children but are wary of too much screen time and its potential deficits in terms of social engagement and physical activity. To address these concerns, related literature suggests technology usages with a blend of digital and physical learning experiences. Towards this end, we developed Kid Space, incorporating immersive computing experiences designed to engage children more actively in physical movement and social collaboration during play-based learning. The technology features an animated peer learner, Oscar, who aims to understand and respond to children's actions and utterances using extensive multimodal sensing and sensemaking technologies. To investigate student engagement during Kid Space learning experiences, an exploratory case study was designed using a formative research method with eight first-grade students. Multimodal data (audio and video) along with observational, interview, and questionnaire data were collected and analyzed. The results show that the students demonstrated high levels of engagement, less attention focused on the screen (projected wall), and more physical activity. In addition to these promising results, the study also enabled us to understand actionable insights to improve Kid Space for future deployments (e.g., the need for real-time personalization). We plan to incorporate the lessons learned from this preliminary study and deploy Kid Space with real-time personalization features for longer periods with more students.

An intelligent tutoring system for supporting active learning: A case study on predictive parsing learning.

The way in which people learn and institutions teach is changing due to the ever-increasing impact of technology. People access the Internet anywhere, anytime and request online training. This has brought about the creation of numerous online learning platforms which offer comprehensive and effective educational solutions which are 100% online. These platforms benefit from intelligent tutoring systems that help and guide students through the learning process, emulating the behavior of a human tutor. However, these systems give the student little freedom to experiment with the knowledge of the subject, that is, they do not allow him/her to propose and carry out tasks on his/her own initiative. They are very restricted systems in term of what the student can do, as the tasks are defined in advance. An intelligent tutoring system is proposed in this paper to encourage students to learn through experimentation, proposing tasks on their own initiative, which involves putting into use all the skills, abilities tools and knowledge needed to successfully solve them. This system has been designed developed and applied for learning predictive parsing techniques and has been used by Computer Science students during four academic courses to evaluate its suitability for improving the student's learning process.

Improving Learner-Computer Interaction through Intelligent Learning Material Delivery Using Instructional Design Modeling.

This paper describes an innovative and sophisticated approach for improving learner-computer interaction in the tutoring of Java programming through the delivery of adequate learning material to learners. To achieve this, an instructional theory and intelligent techniques are combined, namely the Component Display Theory along with content-based filtering and multiple-criteria decision analysis, with the intention of providing personalized learning material and thus, improving student interaction. Until now, the majority of the research efforts mainly focus on adapting the presentation of learning material based on students' characteristics. As such, there is free space for researching issues like delivering the appropriate type of learning material, in order to maintain the pedagogical affordance of the educational software. The blending of instructional design theories and sophisticated techniques can offer a more personalized and adaptive learning experience to learners of computer programming. The paper presents a fully operating intelligent educational software. It merges pedagogical and technological approaches for sophisticated learning material delivery to students. Moreover, it was used by undergraduate university students to learn Java programming for a semester during the COVID-19 lockdown. The findings of the evaluation showed that the presented way for delivering the Java learning material surpassed other approaches incorporating merely instructional models or intelligent tools, in terms of satisfaction and knowledge acquisition.

M-learning in the COVID-19 era: physical vs digital class.

Emerging technologies, such as the development of the Internet of Things and the transition to smart cities, and innovative handheld devices have led to big changes in many aspects of our lives, while more changes were imminent. Education is also a sector that has undergone huge changes due to the spreading of those devices. Even at the era of feature phones, it started to become clear that portable devices with access to the internet can be used for learning. The process of learning with the use of mobile phones was then in an early stage, due to the limitations of feature phones. Whereas, with the introduction of smartphones, education is expected to be drastically altered in the future, in most parts of the world. New, radical, and controversial in some cases, approaches have been developed, over the past years, in an effort to implement a mobile learning process in real life conditions. Intelligent tutoring systems have had rapid growth, especially in the COVID-19 era, while a significant increase in online courses via social networks has also been noted. This paper focuses on presenting the most important research parameters of m-learning during the last decade, while it also incorporates a novel empirical study in the domain. The utilization of educational data has been taken into consideration and is presented, aiming at ways to improve human interaction in the digital classroom.

Comparison and Efficacy of Synergistic Intelligent Tutoring Systems with Human Physiological Response.

The analysis of physiological signals is ubiquitous in health and medical diagnosis as a primary tool for investigation and inquiry. Physiological signals are now being widely used for psychological and social fields. They have found promising application in the field of computer-based learning and tutoring. Intelligent Tutoring Systems (ITS) is a fast-paced growing field which deals with the design and implementation of customized computer-based instruction and feedback methods without human intervention. This paper introduces the key concepts and motivations behind the use of physiological signals. It presents a detailed discussion and experimental comparison of ITS. The synergism of ITS and physiological signals in automated tutoring systems adapted to the learner's emotions and mental states are presented and compared. The insights are developed, and details are presented. The accuracy and classification methods of existing systems are highlighted as key areas of improvement. High-precision measurement systems and neural networks for machine-learning classification are deemed prospective directions for future improvements to existing systems.

A Bayesian Network Meta-Analysis to Synthesize the Influence of Contexts of Scaffolding Use on Cognitive Outcomes in STEM Education.

Computer-based scaffolding provides temporary support that enables students to participate in and become more proficient at complex skills like problem solving, argumentation, and evaluation. While meta-analyses have addressed between-subject differences on cognitive outcomes resulting from scaffolding, none has addressed within-subject gains. This leaves much quantitative scaffolding literature not covered by existing meta-analyses. To address this gap, this study used Bayesian network meta-analysis to synthesize within-subjects (pre-post) differences resulting from scaffolding in 56 studies. We generated the posterior distribution using 20,000 Markov Chain Monte Carlo samples. Scaffolding has a consistently strong effect across student populations, STEM (science, technology, engineering, and mathematics) disciplines, and assessment levels, and a strong effect when used with most problem-centered instructional models (exception: inquiry-based learning and modeling visualization) and educational levels (exception: secondary education). Results also indicate some promising areas for future scaffolding research, including scaffolding among students with learning disabilities, for whom the effect size was particularly large (g = 3.13).

Synthesizing Results From Empirical Research on Computer-Based Scaffolding in STEM Education: A Meta-Analysis.

Computer-based scaffolding assists students as they generate solutions to complex problems, goals, or tasks, helping increase and integrate their higher order skills in the process. However, despite decades of research on scaffolding in STEM (science, technology, engineering, and mathematics) education, no existing comprehensive meta-analysis has synthesized the results of these studies. This review addresses that need by synthesizing the results of 144 experimental studies (333 outcomes) on the effects of computer-based scaffolding designed to assist the full range of STEM learners (primary through adult education) as they navigated ill-structured, problem-centered curricula. Results of our random effect meta-analysis (a) indicate that computer-based scaffolding showed a consistently positive (g = 0.46) effect on cognitive outcomes across various contexts of use, scaffolding characteristics, and levels of assessment and (b) shed light on many scaffolding debates, including the roles of customization (i.e., fading and adding) and context-specific support. Specifically, scaffolding's influence on cognitive outcomes did not vary on the basis of context-specificity, presence or absence of scaffolding change, and logic by which scaffolding change is implemented. Scaffolding's influence was greatest when measured at the principles level and among adult learners. Still scaffolding's effect was substantial and significantly greater than zero across all age groups and assessment levels. These results suggest that scaffolding is a highly effective intervention across levels of different characteristics and can largely be designed in many different ways while still being highly effective.

The effectiveness of argumentation in tutorial dialogues with an Intelligent Tutoring System for genetic risk of breast cancer.

BRCA Gist is an Intelligent Tutoring System that helps women understand issues related to genetic testing and breast cancer risk. In two laboratory experiments and a field experiment with community and web-based samples, an avatar asked 120 participants to produce arguments for and against genetic testing for breast cancer risk. Two raters assessed the number of argumentation elements (claim, reason, backing, etc.) found in response to prompts soliciting arguments for and against genetic testing for breast cancer risk (IRR=.85). When asked to argue for genetic testing, 53.3 % failed to meet the minimum operational definition of making an argument, a claim supported by one or more reasons. When asked to argue against genetic testing, 59.3 % failed to do so. Of those who failed to generate arguments most simply listed disconnected reasons. However, participants who provided arguments against testing (40.7 %) performed significantly higher on a posttest of declarative knowledge. In each study we found positive correlations between the quality of arguments against genetic testing (i.e., number of argumentation elements) and genetic risk categorization scores. Although most interactions did not contain two or more argument elements, when more elements of arguments were included in the argument against genetic testing interaction, participants had greater learning outcomes. Apparently, many participants lack skills in making coherent arguments. These results suggest an association between argumentation ability (knowing how to make complex arguments) and subsequent learning. Better education in developing arguments may be necessary for people to learn from generating arguments within Intelligent Tutoring Systems and other settings.

METACOGNITIVE SCAFFOLDS IMPROVE SELF-JUDGMENTS OF ACCURACY IN A MEDICAL INTELLIGENT TUTORING SYSTEM.

In this study, we examined the effect of two metacognitive scaffolds on the accuracy of confidence judgments made while diagnosing dermatopathology slides in SlideTutor. Thirty-one (N = 31) first- to fourth-year pathology and dermatology residents were randomly assigned to one of the two scaffolding conditions. The cases used in this study were selected from the domain of Nodular and Diffuse Dermatitides. Both groups worked with a version of SlideTutor that provided immediate feedback on their actions for two hours before proceeding to solve cases in either the Considering Alternatives or Playback condition. No immediate feedback was provided on actions performed by participants in the scaffolding mode. Measurements included learning gains (pre-test and post-test), as well as metacognitive performance, including Goodman-Kruskal Gamma correlation, bias, and discrimination. Results showed that participants in both conditions improved significantly in terms of their diagnostic scores from pre-test to post-test. More importantly, participants in the Considering Alternatives condition outperformed those in the Playback condition in the accuracy of their confidence judgments and the discrimination of the correctness of their assertions while solving cases. The results suggested that presenting participants with their diagnostic decision paths and highlighting correct and incorrect paths helps them to become more metacognitively accurate in their confidence judgments.

"Better than my professor?" How to develop artificial intelligence tools for higher education.

Artificial Intelligence (AI) tools are currently designed and tested in many fields to improve humans' ability to make decisions. One of these fields is higher education. For example, AI-based chatbots ("conversational pedagogical agents") could engage in conversations with students in order to provide timely feedback and responses to questions while the learning process is taking place and to collect data to personalize the delivery of course materials. However, many existent tools are able to perform tasks that human professionals (educators, tutors, professors) could perform, just in a timelier manner. While discussing the possible implementation of AI-based tools in our university's educational programs, we reviewed the current literature and identified a number of capabilities that future AI solutions may feature, in order to improve higher education processes, with a focus on distance higher education. Specifically, we suggest that innovative tools could influence the methodologies by which students approach learning; facilitate connections and information attainment beyond course materials; support the communication with the professor; and, draw from motivation theories to foster learning engagement, in a personalized manner. Future research should explore high-level opportunities represented by AI for higher education, including their effects on learning outcomes and the quality of the learning experience as a whole.

Intelligent Tutoring Systems, Generative Artificial Intelligence (AI), and Healthcare Agents: A Proof of Concept and Dual-Layer Approach.

This study introduces a novel methodology for enhancing intelligent tutoring systems (ITS) through the integration of generative artificial intelligence (GenAI) and specialized AI agents. We present a proof of concept (PoC) demo that implements a dual-layer GenAI validation approach that utilizes multiple large language models to ensure the reliability and pedagogical integrity of the AI-generated content. The system features role-specific AI agents, a GenAI-powered scoring mechanism, and an AI mentor that provides periodic guidance. This approach demonstrates capabilities in dynamic scenario generation and real-time adaptability while addressing key challenges in AI-driven education, such as personalization, scalability, and domain-specific knowledge integration. Although exemplified here through a case study in healthcare root cause analysis, the methodology is designed for broad applicability across various fields. Our findings suggest that this approach has significant potential for advancing adaptive learning and personalized instruction while raising important considerations regarding ethical AI application in education. This work provides a foundation for further research into the efficacy and impact of GenAI-enhanced ITS on learning outcomes and instructional design across diverse educational domains.

rDSA : an intelligent tool for data science assignments.

Tools supporting the teaching and learning of programming may help professors in correcting assignments and students in receiving immediate feedback, thus improving the solution before the final submission. This paper describes the rDSA tool, which was designed, developed, and evaluated to support students in completing assignments concerning (i) the execution of statistical analyses in the R language and (ii) commenting on the results in natural language. The paper focuses on the feedback provided by the tool to students and how it was designed/evaluated/improved over the years. The paper also presents the results of two studies that indicate the advantages of using the tool in terms of engagement and learning outcomes. To conclude, we provide a discussion on the characteristics of the tool, its use in similar courses, and the scope for future work.

A Survey of Current Machine Learning Approaches to Student Free-Text Evaluation for Intelligent Tutoring.

Recent years have seen increased interests in applying the latest technological innovations, including artificial intelligence (AI) and machine learning (ML), to the field of education. One of the main areas of interest to researchers is the use of ML to assist teachers in assessing students' work on the one hand and to promote effective self-tutoring on the other hand. In this paper, we present a survey of the latest ML approaches to the automated evaluation of students' natural language free-text, including both short answers to questions and full essays. Existing systematic literature reviews on the subject often emphasise an exhaustive and methodical study selection process and do not provide much detail on individual studies or a technical background to the task. In contrast, we present an accessible survey of the current state-of-the-art in student free-text evaluation and target a wider audience that is not necessarily familiar with the task or with ML-based text analysis in natural language processing (NLP). We motivate and contextualise the task from an application perspective, illustrate popular feature-based and neural model architectures and present a selection of the latest work in the area. We also remark on trends and challenges in the field.

Lessons Learned and Future Directions of MetaTutor: Leveraging Multichannel Data to Scaffold Self-Regulated Learning With an Intelligent Tutoring System.

Self-regulated learning (SRL) is critical for learning across tasks, domains, and contexts. Despite its importance, research shows that not all learners are equally skilled at accurately and dynamically monitoring and regulating their self-regulatory processes. Therefore, learning technologies, such as intelligent tutoring systems (ITSs), have been designed to measure and foster SRL. This paper presents an overview of over 10 years of research on SRL with MetaTutor, a hypermedia-based ITS designed to scaffold college students' SRL while they learn about the human circulatory system. MetaTutor's architecture and instructional features are designed based on models of SRL, empirical evidence on human and computerized tutoring principles of multimedia learning, Artificial Intelligence (AI) in educational systems for metacognition and SRL, and research on SRL from our team and that of other researchers. We present MetaTutor followed by a synthesis of key research findings on the effectiveness of various versions of the system (e.g., adaptive scaffolding vs. no scaffolding of self-regulatory behavior) on learning outcomes. First, we focus on findings from self-reports, learning outcomes, and multimodal data (e.g., log files, eye tracking, facial expressions of emotion, screen recordings) and their contributions to our understanding of SRL with an ITS. Second, we elaborate on the role of embedded pedagogical agents (PAs) as external regulators designed to scaffold learners' cognitive and metacognitive SRL strategy use. Third, we highlight and elaborate on the contributions of multimodal data in measuring and understanding the role of cognitive, affective, metacognitive, and motivational (CAMM) processes. Additionally, we unpack some of the challenges these data pose for designing real-time instructional interventions that scaffold SRL. Fourth, we present existing theoretical, methodological, and analytical challenges and briefly discuss lessons learned and open challenges.

Affective Response Categories-Toward Personalized Reactions in Affect-Adaptive Tutoring Systems.

Affect-adaptive tutoring systems detect the current emotional state of the learner and are capable of adequately responding by adapting the learning experience. Adaptations could be employed to manipulate the emotional state in a direction favorable to the learning process; for example, contextual help can be offered to mitigate frustration, or lesson plans can be accelerated to avoid boredom. Safety-critical situations, in which wrong decisions and behaviors can have fatal consequences, may particularly benefit from affect-adaptive tutoring systems, because accounting for affecting responses during training may help develop coping strategies and improve resilience. Effective adaptation, however, can only be accomplished when knowing which emotions benefit high learning performance in such systems. The results of preliminary studies indicate interindividual differences in the relationship between emotion and performance that require consideration by an affect-adaptive system. To that end, this article introduces the concept of Affective Response Categories (ARCs) that can be used to categorize learners based on their emotion-performance relationship. In an experimental study, N = 50 subjects (33% female, 19-57 years, M = 32.75, SD = 9.8) performed a simulated airspace surveillance task. Emotional valence was detected using facial expression analysis, and pupil diameters were used to indicate emotional arousal. A cluster analysis was performed to group subjects into ARCs based on their individual correlations of valence and performance as well as arousal and performance. Three different clusters were identified, one of which showed no correlations between emotion and performance. The performance of subjects in the other two clusters benefitted from negative arousal and differed only in the valence-performance correlation, which was positive or negative. Based on the identified clusters, the initial ARC model was revised. We then discuss the resulting model, outline future research, and derive implications for the larger context of the field of adaptive tutoring systems. Furthermore, potential benefits of the proposed concept are discussed and ethical issues are identified and addressed.

Artificial Intelligence in Education (AIEd): a high-level academic and industry note 2021.

In the past few decades, technology has completely transformed the world around us. Indeed, experts believe that the next big digital transformation in how we live, communicate, work, trade and learn will be driven by Artificial Intelligence (AI) [83]. This paper presents a high-level industrial and academic overview of AI in Education (AIEd). It presents the focus of latest research in AIEd on reducing teachers' workload, contextualized learning for students, revolutionizing assessments and developments in intelligent tutoring systems. It also discusses the ethical dimension of AIEd and the potential impact of the Covid-19 pandemic on the future of AIEd's research and practice. The intended readership of this article is policy makers and institutional leaders who are looking for an introductory state of play in AIEd.

The Role of Self-Improving Tutoring Systems in Fostering Pre-Service Teacher Self-Regulated Learning.

Computer-based learning environments serve as a valuable asset to help strengthen teacher preparation and preservice teacher self-regulated learning. One of the most important advantages is the opportunity to collect ambient data unobtrusively as observable indicators of cognitive, affective, metacognitive, and motivational processes that mediate learning and performance. Ambient data refers to teacher interactions with the user interface that include but are not limited to timestamped clickstream data, keystroke and navigation events, as well as document views. We review the claim that computers designed as metacognitive tools can leverage the data to serve not only teachers in attaining the aims of instruction, but also researchers in gaining insights into teacher professional development. In our presentation of this claim, we review the current state of research and development of a network-based tutoring system called nBrowser, designed to support teacher instructional planning and technology integration. Network-based tutors are self-improving systems that continually adjust instructional decision-making based on the collective behaviors of communities of learners. A large part of the artificial intelligence resides in semantic web mining, natural language processing, and network algorithms. We discuss the implications of our findings to advance research into preservice teacher self-regulated learning.

Automatic Detection of a Student's Affective States for Intelligent Teaching Systems.

AutoTutor is an automated computer tutor that simulates human tutors and holds conversations with students in natural language. Using data collected from AutoTutor, the following determinations were sought: Can we automatically classify affect states from intelligent teaching systems to aid in the detection of a learner's emotional state? Using frequency patterns of AutoTutor feedback and assigned user emotion in a series of pairs, can the next pair of feedback/emotion series be predicted? Through a priori data mining approaches, we found dominant frequent item sets that predict the next set of responses. Thirty-four participants provided 200 turns between the student and the AutoTutor. Two series of attributes and emotions were concatenated into one row to create a record of previous and next set of emotions. Feature extraction techniques, such as multilayer-perceptron and naive Bayes, were performed on the dataset to perform classification for affective state labeling. The emotions 'Flow' and 'Frustration' had the highest classification of all the other emotions when measured against other emotions and their respective attributes. The most common frequent item sets were 'Flow' and 'Confusion'.

"Individualized learning in a course with a tight schedule".

The article presents a solution supporting individualised learning in courses with a tight schedule. Such courses pose additional organisational challenges and require appropriate tools. The presented solution is based on an Intelligent Tutoring System immersed in repository of e-learning content, which enables selection of content immediately before its provision to the student instead of at the beginning of a course. Thanks to this, the system, having identified the student's needs, is able to make available the most suitable repository content at a given stage of education. The flexibility of the system is guaranteed by modularisation of content and its logical division using the UCTS taxonomy. The content has been described by means of concepts arranged according to the specificity of the domain to which the resources belong in order to ensure that the ITS is able to select relevant content. The proposed solution was used to set up an Applications of Fuzzy Logic course, which was part of an Artificial Intelligence class. The course was conducted within a very limited time frame resulting from the COVID-19 epidemic.