Multimodal Interaction System Supported by Digital Humans
Bibliographic record
Abstract
As digital services continue to grow in popularity, there is an increasing need for systems that replicate human interaction while prioritizing user satisfaction and engagement. Early implementations offered interactions that felt unnatural, mainly due to the lack of realistic facial expressions and movement in character animations. Over time, however, significant advancements—particularly from the video game industry—have driven major improvements in this field. Titles such as Senua’s Saga: Hellblade II and Black Myth: Wukong illustrate how these developments have enabled the creation of immersive characters with highly realistic facial animation. The Metaverse has emerged as a key area of interest, offering immersive virtual environments where users interact within a shared digital space. This evolution has increased the demand for personalized Digital Humans—high-fidelity, computer-generated avatars capable of expressing empathy in real time. This study examines how Digital Humans can enhance human–computer interaction by reducing the emotional disconnect commonly associated with automated systems. Such avatars show potential across remote meetings, customer service, online education, and Metaverse platforms, fostering more natural and engaging interactions. Emotionally expressive Digital Humans were created using the MetaHuman framework and Unreal Engine, incorporating multimodal MoCap based on computer vision and RGB camera input. Two user tests were conducted: one focused on facial expressions and another combining facial expressions with full-body movement, involving a total of 40 participants. Empathy levels were assessed using the Toronto Empathy Questionnaire (TEQ), administered before and after interaction. One-Way ANOVA analyses showed no statistically significant differences in elicited empathy between default and custom animations. In the facial-animation test, participants’ average TEQ scores were 47.4 for default animations and 45.0 for custom ones, both within or above the general population average (40–45). In the combined full-body test, mean scores were 47.6 for human body movement and 45.5 for MetaHuman body motion. Although personalization did not significantly outperform default animations, the results highlight the essential role of realistic body movement in shaping emotional perception and interaction quality. The findings confirm that emotionally expressive Digital Humans can be effectively integrated into digital platforms, while showing that facial personalization alone must be complemented by contextual and narrative elements to maximize empathetic impact. This work provides a solid foundation for future research on deploying Digital Humans in real-world interactive systems.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.018 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".