How Embodiment Shapes Human–AI Interaction: Evidence from Real-World Deployment of Holographic and Screen-Based Systems

Artificial intelligence (AI) is increasingly moving into physical environments through kiosks, avatars, and holographic systems. While significant research has focused on model performance, less is understood about how the form of AI systems influences human interaction. This study examines the impact of embodiment by comparing user interactions with a holographic AI assistant and a screen-based avatar deployed at CES. Observational and interaction data reveal that the holographic system consistently elicited longer engagement, more exploratory questioning, and greater user interaction than the screen-based system. Notably, these differences occurred despite both systems using the same underlying AI model. The findings suggest that embodiment shapes user behavior independent of system functionality. This work contributes a practical framework for evaluating embodied AI systems and highlights the importance of considering physical form in the design of future human–AI interactions. This work presents a behavioral evaluation framework for embodied AI systems that leverages interaction time, question style, user behavior, and language use.

Artificial intelligence; human–AI interaction

1. Aljaroodi, H. M., Adam, M., Chiong, R., & Teubner, T. (2019). Avatars and embodied agents in informationsystems research: A systematic review and conceptual framework. Open Research Newcastle. https://hdl.handle.net/1959.13/1413609 [Google Scholar] [Crossref]

2. Bansal, G., Chamola, V., Hussain, A., et al. (2024). Transforming conversations with AI—A comprehensive study of ChatGPT. Cognitive Computation, 16, 2487–2510. https://doi.org/10.1007/s12559-023-10236-2 [Google Scholar] [Crossref]

3. Johnson, L., Inamdar, A. H., & Yadecha, B. L. (2026). From AI stack to cognitive stack: A semantic–spatial–relational architecture for trustworthy AI. Trends in Computer Science and Information Technology.https://doi.org/10.17352/tcsit.000105 [Google Scholar] [Crossref]

4. Johnson, L., Sudhir, A. D., & Padmapriya, A. A. (2025). The feel of friendship: Emotional presence and relationalauthenticity in large language models. International Journal of Humanities and Social Science, 15. https://doi.org/10.30845/ijhss.vol15p29 [Google Scholar] [Crossref]

5. Marconi, L., Longo, L., & Cabitza, F. (2026). Assessing Interaction Quality in Human–AI Dialogue: AnIntegrative Review and Multi-Layer Framework for Conversational Agents. Machine Learning andKnowledge Extraction, 8(2), 28. https://doi.org/10.3390/make8020028 [Google Scholar] [Crossref]

6. Seinfeld, S., Feuchtner, T., Maselli, A., & Müller, J. (2021). User representations in human–computer interaction.Human–Computer Interaction, 36(5–6), 400–438. https://doi.org/10.1080/07370024.2020.1724790 [Google Scholar] [Crossref]

7. van Vugt, H.C., Hoorn, J.F. and Konijn, E.A. (2009), Interactive engagement with embodied agents: anempirically validated framework. Comp. Anim. Virtual Worlds, 20: 195-204. https://doi.org/10.1002/cav.312 [Google Scholar] [Crossref]

• The Role of Artificial Intelligence in Revolutionizing Library Services in Nairobi: Ethical Implications and Future Trends in User Interaction
• ESPYREAL: A Mobile Based Multi-Currency Identifier for Visually Impaired Individuals Using Convolutional Neural Network
• Comparative Analysis of AI-Driven IoT-Based Smart Agriculture Platforms with Blockchain-Enabled Marketplaces
• AI-Based Dish Recommender System for Reducing Fruit Waste through Spoilage Detection and Ripeness Assessment
• SEA-TALK: An AI-Powered Voice Translator and Southeast Asian Dialects Recognition