Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Learning Through AI-Clones: Enhancing Self-Perception and Presentation Performance

Qingxiao Zheng, Zhuoer Chen, Yun Huang

TL;DR

This paper addresses the challenge of improving online self-presentation for international speakers by introducing AI-generated self-clones as relatable, aspirational role models guided by social comparison theory and regulatory focus. The authors implement a mixed-design experiment (n=44) comparing self-recorded versus AI-clone videos, with AI-clones manipulated along promotion and prevention orientations. Key findings show immediate speech-quantity improvements and increased self-kindness for AI-clones, while self-recordings yield greater pronunciation satisfaction; regulatory focus modulates learning experience and certain performance metrics, with promotion-focused learners reporting stronger perceived benefits. The work highlights practical potential for AI-based personalized feedback in language learning, while emphasizing ethical, identity, and accessibility considerations for deploying clones in education.

Abstract

This study examines the impact of AI-generated digital clones with self-images on enhancing perceptions and skills in online presentations. A mixed-design experiment with 44 international students compared self-recording videos (self-recording group) to AI-clone videos (AI-clone group) for online English presentation practice. AI-clone videos were generated using voice cloning, face swapping, lip-syncing, and body-language simulation, refining the repetition, filler words, and pronunciation of participants' original presentations. Through the lens of social comparison theory, the results showed that AI clones functioned as positive "role models" for facilitating social comparisons. When comparing the effects on self-perceptions, speech qualities, and self-kindness, the self-recording group showed an increase in pronunciation satisfaction. However, the AI-clone group exhibited greater self-kindness, broader observational coverage, and a meaningful transition from a corrective to an enhancive approach in self-critique. Moreover, machine-rated scores revealed immediate performance gains only within the AI-clone group. Considering individual differences, aligning interventions with participants' regulatory focus significantly enhanced their learning experience. These findings highlight the theoretical, practical, and ethical implications of AI clones in supporting emotional and cognitive skill development.

Learning Through AI-Clones: Enhancing Self-Perception and Presentation Performance

TL;DR

This paper addresses the challenge of improving online self-presentation for international speakers by introducing AI-generated self-clones as relatable, aspirational role models guided by social comparison theory and regulatory focus. The authors implement a mixed-design experiment (n=44) comparing self-recorded versus AI-clone videos, with AI-clones manipulated along promotion and prevention orientations. Key findings show immediate speech-quantity improvements and increased self-kindness for AI-clones, while self-recordings yield greater pronunciation satisfaction; regulatory focus modulates learning experience and certain performance metrics, with promotion-focused learners reporting stronger perceived benefits. The work highlights practical potential for AI-based personalized feedback in language learning, while emphasizing ethical, identity, and accessibility considerations for deploying clones in education.

Abstract

This study examines the impact of AI-generated digital clones with self-images on enhancing perceptions and skills in online presentations. A mixed-design experiment with 44 international students compared self-recording videos (self-recording group) to AI-clone videos (AI-clone group) for online English presentation practice. AI-clone videos were generated using voice cloning, face swapping, lip-syncing, and body-language simulation, refining the repetition, filler words, and pronunciation of participants' original presentations. Through the lens of social comparison theory, the results showed that AI clones functioned as positive "role models" for facilitating social comparisons. When comparing the effects on self-perceptions, speech qualities, and self-kindness, the self-recording group showed an increase in pronunciation satisfaction. However, the AI-clone group exhibited greater self-kindness, broader observational coverage, and a meaningful transition from a corrective to an enhancive approach in self-critique. Moreover, machine-rated scores revealed immediate performance gains only within the AI-clone group. Considering individual differences, aligning interventions with participants' regulatory focus significantly enhanced their learning experience. These findings highlight the theoretical, practical, and ethical implications of AI clones in supporting emotional and cognitive skill development.
Paper Structure (67 sections, 4 figures, 6 tables)

This paper contains 67 sections, 4 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Urgent Needs and Approaches for Practicing Online Self-Presentation
  4. Limitations of Current Feedback Systems
  5. Challenges of Learning from Role Models
  6. The Potential of Using AI-clones as Role Models
  7. Theoretical Lens: Social Comparison Theory and Individual Regulatory Focus
  8. H1 (self-recording group v.s. AI-clone group)
  9. Self-perception
  10. Speech Quality
  11. Self-kindness
  12. H2 (AI-clone group: Promotion focus v.s. Prevention focus)
  13. Learning Experience
  14. Self-perception
  15. Speech Quality
  16. ...and 52 more sections

Figures (4)

  • Figure 1: AI-clones with participants' chosen Avatar template (Images are shared with participants' permission)
  • Figure 2: Study procedure: all participants engaged in the five steps (detailed in Section 3.2).
  • Figure 3: Pre-test and Post-test self-perceptions towards the rated 9 items of speech performance. While many improvements were found within both groups, only Satisfaction in Pronunciation yielded a significant difference between groups.
  • Figure 4: Pre-test and Post-test Scores of Speech Quality for the Self-Recording and AI-Clone Group: Only pacing control yielded a significant difference between groups. 1st is original, 2nd is after trained.