Sürdürülebilir Kalkınma Amaçları

• 2

• MakaleYayıncıda açık erişim2026Scopus SJRQ1/r/munzur/895
  Thematic Structure of Pedagogical Agent Studies: LDA Analysis for the Period 2020–2025

  Turgut, Yigit Emrah; Aktı Aslan, Seda; Kopuz, Tuba; Aslan, Alper; Allison, Jordan; Özyurt, Özcan

  This study examines 2,360 pedagogical agent (PA) articles published between 2020 and 2025 to identify thematic structures, trends, and research gaps through bibliometric analysis and LDA-based topic modeling. The optimal model produced 10 themes (c_v = 0.4767). The dominant themes—Learner Interaction with Virtual Assistants in Education, Student-Centred Learning and Individual Guidance, and NLP Foundations for Pedagogical Agents—account for 51.3% of publications. Trend analyses revealed consistent growth in both Artificial Intelligence and Pedagogical Design in Education and NLP Foundations for Pedagogical Agents, while Learner Interaction with Virtual Assistants in Education reached saturation. Interaction network results showed these themes at the conceptual core of the field, whereas AI-Driven Medical Chatbots, Knowledge-Based Learning Models, and Student Experiences in Intelligent Learning Environments emerged as future research areas. Overall, findings highlight a strong thematic shift toward artificial intelligence, natural language processing, and student-centered learning.

  • 
  İncele
• MakaleAçık Erişim2026Scopus SJRQ1/r/munzur/627
  The Strategic Use of Instructor Visibility in Educational Videos: An Eye-Tracking Data-Based Study

  Türel, Yalın Kılıç; Alpsülün, Mustafa; Yuruk, Süleyman Eren; Aslan, Alper; Kokoç, Mehmet; Polat, Hamza; Öztürk Akca, Cemile; Kurşun, Engin

  This study developed an exploratory heuristic decision-support framework for dynamically regulating instructor visibility in instructional videos based on learners’ eye-tracking data. Eye-movement data were collected from 40 university students using a Tobii Pro Fusion while viewing 16 explanatory and procedural instructional videos. Instructor and Learning Content Areas of Interest were analyzed using normalized eye-tracking indicators. Descriptive analyses were complemented by Wilcoxon signed-rank tests, binary logistic regression, and receiver operating characteristic (ROC) analyses. Learners allocated significantly greater visual attention to learning content than to the instructor across both video types. Logistic regression identified instructor attention percentage, visit-related metrics, and blink frequency as significant predictors of visibility decisions. ROC analysis showed that instructor attention percentage provided the highest discriminative performance, with an optimal threshold of approximately 30%. Findings suggest that instructor visibility may be particularly appropriate during introductory, summary, and conceptually demanding segments, providing empirically grounded, attention-aware guidance for adaptive instructional video interfaces.

  • 
  İncele