Stimulating and sustaining interest in a language course: An experimental comparison of Chatbot and Human task partners

Computers in Human Behavior, Год журнала: 2017, Номер 75, С. 461 - 468

Опубликована: Май 31, 2017

Язык: Английский

---

Advancing the Science of Collaborative Problem Solving

Psychological Science in the Public Interest, Год журнала: 2018, Номер 19(2), С. 59 - 92

Опубликована: Ноя. 1, 2018

Collaborative problem solving (CPS) has been receiving increasing international attention because much of the complex work in modern world is performed by teams. However, systematic education and training on CPS lacking for those entering participating workforce. In 2015, Programme International Student Assessment (PISA), a global test educational progress, documented low levels proficiency CPS. This result not only underscores significant societal need but also presents an important opportunity psychological scientists to develop, adopt, implement theory empirical research with educators policy experts improve article offers some directions science participate growing throughout world. First, it identifies existing theoretical frameworks that focus Second, provides examples how recent technologies can automate analyses processes assessments so substantially larger data sets be analyzed students receive immediate feedback their performance. Third, challenges, debates, uncertainties creating infrastructure research, education, assessment are expected when supported informed science. will require interdisciplinary efforts include expertise science, assessment, intelligent digital technologies, policy.

Язык: Английский

---

Educational applications of artificial intelligence in simulation-based learning: A systematic mapping review

Computers and Education Artificial Intelligence, Год журнала: 2022, Номер 3, С. 100087 - 100087

Опубликована: Янв. 1, 2022

The field of education has experienced a transformation as artificial intelligence (AI) becomes increasingly applicable for learning purposes. AI the potential to transform social interactions in educational contexts among learners, teachers, and technologies. In this systematic mapping review, we focus on framing trends applications simulation-based learning. Fifty-nine studies met inclusion exclusion criteria. We coded analyzed six mapped categories literature review: (1) year-of-study trend, (2) methods, (3) technologies, (4) simulation, (5) study trends, (6) principles theories. To provide nuanced details from included literature, also synthesized three thematic trends: built virtual agents learning, infused with affective computing, leveraged assessments. Trend One builds general acknowledgement guide situated Two posits role states trajectories suggests related machine approaches. Three discusses techniques multimodal computing used assessment feedback. paper concludes implications suggestions research practice using

Язык: Английский

---

Chatbot to improve learning punctuation in Spanish and to enhance open and flexible learning environments

International Journal of Educational Technology in Higher Education, Год журнала: 2021, Номер 18(1)

Опубликована: Июнь 27, 2021

Abstract The objective of this article is to analyze the didactic functionality a chatbot improve results students National University Distance Education (UNED / Spain) in accessing university subject Spanish Language. For this, quasi-experimental experiment was designed, and quantitative methodology used through pretest posttest control experimental group which effectiveness two teaching models compared, one more traditional based on exercises written paper another interaction with chatbot. Subsequently, perception an academic forum about educational use analyzed text mining tests Latent Dirichlet Allocation (LDA), pairwise distance matrix bigrams. showed that substantially improved compared (experimental mean: 32.1346 28.4706). Punctuation correctness has been mainly usage comma, colon periods different syntactic patterns. Furthermore, they positively value chatbots their teaching–learning process three dimensions: greater “support” companionship learning process, as perceive interactivity due conversational nature; “feedback” and, lastly, especially ease possibility interacting anywhere anytime.

Язык: Английский

---

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

Frontiers in Psychology, Год журнала: 2022, Номер 13

Опубликована: Июнь 14, 2022

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

Язык: Английский

---

BreastScreening-AI: Evaluating medical intelligent agents for human-AI interactions

Artificial Intelligence in Medicine, Год журнала: 2022, Номер 127, С. 102285 - 102285

Опубликована: Март 29, 2022

In this paper, we developed BreastScreening-AI within two scenarios for the classification of multimodal beast images: (1) Clinician-Only; and (2) Clinician-AI. The novelty relies on introduction a deep learning method into real clinical workflow medical imaging diagnosis. We attempt to address three high-level goals in above scenarios. Concretely, how clinicians: i) accept interact with these systems, revealing whether are explanations functionalities required; ii) receptive AI-assisted by providing benefits from mitigating error; iii) affected AI assistance. conduct an extensive evaluation embracing following experimental stages: (a) patient selection different severities, (b) qualitative quantitative analysis chosen patients under through real-world case study 45 clinicians nine institutions. compare diagnostic observe superiority Clinician-AI scenario, as obtained decrease 27% False-Positives 4% False-Negatives. Through study, conclude that proposed design techniques positively impact expectations perceptive satisfaction 91% clinicians, while decreasing time-to-diagnose 3 min per patient.

Язык: Английский

---

The Effect of Digital Game-Based Learning Interventions on Cognitive, Metacognitive, and Affective-Motivational Learning Outcomes in School: A Meta-Analysis

Review of Educational Research, Год журнала: 2023, Номер 94(2), С. 193 - 227

Опубликована: Май 9, 2023

Digital game-based learning (DGBL) interventions can be superior to traditional instruction methods for learning, but previous meta-analyses covered a huge period and included variety of different target groups, limiting the results’ transfer on specific groups. Therefore, aim this meta-analysis is theory-based examination DGBL interventions’ effects outcomes (cognitive, metacognitive, affective-motivational) in school context, using studies published between 2015 2020 meta-analytic techniques (including moderator analyses) examine effectiveness compared methods. Results from random-effects models revealed significant medium effect overall (g = .54) cognitive .67). Also found were small affective-motivational .32) no metacognitive outcomes. Additionally, there was evidence publication bias. Further meta-regression did not reveal moderating personal, environmental, or confounding factors. The findings partially support positive impact school, study addresses its practical implications.

Язык: Английский

---

Online Assessment in Higher Education: A Systematic Review

Online Learning, Год журнала: 2023, Номер 27(1)

Опубликована: Март 1, 2023

Online assessment is defined as a systematic method of gathering information about learner and learning processes to draw inferences the learner’s dispositions. assessments provide opportunities for meaningful feedback interactive support learners well possible influences on engagement outcomes. The purpose this literature review identify synthesize original research studies focusing online in higher education. Out an initial set 4,290 publications, final sample 114 key publications was identified, according predefined inclusion criteria. synthesis yielded four main categories modes: peer, teacher, automated, self-assessment. findings supports assumption that have promising potential supporting improving A summary success factors implementing includes instructional clear-defined Future may focus harnessing formative summative data from stakeholders environments facilitate real-time help decision-makers improve environments, i.e., analytics-

Язык: Английский

---

Personalized learning through AI

Advances in Engineering Innovation, Год журнала: 2023, Номер 5(1), С. 16 - 19

Опубликована: Дек. 25, 2023

The realm of education is witnessing a transformative integration with Artificial Intelligence (AI), poised to redefine the contours pedagogical strategies. Central this transformation emergence personalized learning experiences, where AI endeavors tailor educational content and interactions resonate individual learners' unique needs, preferences, pace. This paper delves into multifaceted dimensions AI-driven learning, from its potential enhance e-learning modules, advent AI-powered virtual tutors, ethical challenges it surfaces. As tapestry becomes more intertwined digital innovations, understanding AI's role in individualizing paramount.

Язык: Английский

---

A gender matching effect in learning with pedagogical agents in an immersive virtual reality science simulation

Journal of Computer Assisted Learning, Год журнала: 2018, Номер 35(3), С. 349 - 358

Опубликована: Ноя. 29, 2018

Abstract The main objective of this study is to determine whether boys and girls learn better when the characteristics pedagogical agent are matched gender learner while learning in immersive virtual reality (VR). Sixty‐six middle school students (33 females) were randomly assigned about laboratory safety with one two agents: Marie or a drone, who we predicted serve as role models for females males, respectively. results indicated that there significant interactions dependent variables performance during learning, retention, transfer, performing ( d = 0.98, 0.67, 1.03; performance, respectively) drone −0.41, −0.45, −0.23, respectively). suggest gender‐specific design agents may play an important VR environments.

Язык: Английский

---