Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Learning Gain and User Experience of AI Avatar-Based and Human-Presented Explainer Videos: Prospective Randomized

Mike Reichert1, Thorsten Jungmann2, Ute von Jan1,3

  • 1Department of Digital Medicine, Medical School OWL, Bielefeld University, Bielefeld, North Rhine-Westphalia, Germany.

JMIR Formative Research
|June 16, 2026
PubMed
Summary

Related Concept Videos

Crossover Experiments01:16

Crossover Experiments

Crossover experiments, also called the repeated-measurements design, is a study design in which all experimental units are exposed to all treatments in different periods. Crossover experiments are generally used in psychology, the pharmaceutical industry, agriculture, and medicine.
Crossover designs are performed even with smaller sample sizes since the samples can act as their controls. These are better than simple randomized trials since patients are exposed to all the treatments.

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Identifying Gravity-Related Artifacts on Ballistocardiography Signals by Comparing Weightlessness and Normal Gravity Recordings (ARTIFACTS): Protocol for an Observational Study.

JMIR research protocols·2024
Same author

Teaching Digital Medicine to Undergraduate Medical Students With an Interprofessional and Interdisciplinary Approach: Development and Usability Study.

JMIR medical education·2024
Same author

Automated Heart Rate Detection in Seismocardiograms Using Electrocardiogram-Based Algorithms-A Feasibility Study.

Bioengineering (Basel, Switzerland)·2024
Same author

Prolonged mHealth-Based Arrhythmia Monitoring in Patients With Hypertrophic Cardiomyopathy (HCM-PATCH): Protocol for a Single-Center Cohort Study.

JMIR research protocols·2023
Same author

Development of Open Backend Structures for Health Care Professionals to Improve Participation in App Developments: Pilot Usability Study of a Medical App.

JMIR formative research·2023
Same author

Proposal of a New Rating Concept for Digital Health Applications in Orthopedics and Traumatology.

International journal of environmental research and public health·2022

AI avatars and human presenters in educational videos yield similar learning gains, but students prefer human presenters for a better user experience. This study explored AI in higher education.

Area of Science:

  • Educational Technology
  • Artificial Intelligence in Education

Background:

  • Explainer videos are common in higher education.
  • The impact of AI-generated avatars versus human presenters on learning and user experience is not well understood, especially in technical fields.

Purpose of the Study:

  • To evaluate the feasibility of a randomized crossover design for comparing AI avatars and human presenters in educational videos.
  • To assess learning gains and user experience differences between AI-generated avatar and human presenter formats.

Main Methods:

  • A randomized crossover feasibility study with 13 undergraduate engineering students.
  • Participants viewed content-identical explainer videos on fuel cell technology presented by an AI avatar and a human presenter.
  • Learning gains were measured via knowledge tests; user experience was assessed using the AttrakDiff2 questionnaire.
Keywords:
AIAI avatarsartificial intelligenceartificial intelligence avatarscrossover studydigital learningexplainer videosfeasibility studyhigher educationlearning gainuser experience

Related Experiment Videos

Main Results:

  • Both AI avatars and human presenters resulted in significant short-term learning gains.
  • No statistically significant difference in learning gains was found between AI avatar and human presenter formats (P=.51).
  • User experience ratings were significantly higher for the human presenter, while AI avatars were perceived as neutral.

Conclusions:

  • Investigating AI-based explainer videos is feasible, but crossover designs present challenges.
  • While short-term learning gains were comparable, human presenters were preferred for user experience.
  • Further research with larger samples and refined methodologies is recommended to confirm these findings.