Universal Village Oriented Solution for Elderly Emotional Support
DOI:
https://doi.org/10.63313/JCSFT.2003Keywords:
Smart healthcare, conversational AI, Emotional Support, Universal Village, elderly care, sustainability, AI hallucination mitigation, closed feedback control loop, information security, multi-model information, data analysisAbstract
As the global population continues to age, the number of the elderly significantly grows. The aging of the body, combined with the awareness of physical decline, can negatively affect the elderly's mental health [4]. The negative impacts on physical and mental health caused by loneliness and social isolation could increase the use of healthcare services, leading to burdens on the healthcare system [2]. The gradually decreasing potential support ratio also increases the pressure on society to provide care for the elderly [1]. This means that the problems of elderly care are becoming a growing challenge for the working-age population. Loneliness could be improved by interactions [2], and the emergence of large language models (LLMs) allows smart technologies to manage interactions. In the past, chatbots based on smart technology had limited levels of personalization and emotional interaction. However, achieving greater personalization requires collecting more user information, which can lead to privacy concerns [3]. This study uses a literature review approach to examine existing research in smart technologies from Universal Village's perspectives. We propose an elderly emotional support chatbot with emotional understanding and personalized memory management that can effectively mitigate LLM hallucination, enhance information security, and increase privacy protection. This could enhance elderly's mental health and improve the quality of life, reducing the burden on family caregivers and the healthcare system.
References
[1] United Nations, Department of Economic and Social Affairs, Population Division (2019). World Population Prospects 2019: Highlights.
[2] Berg-Weger M, Morley J. Editorial: Loneliness in Old Age: An unaddressed Health Problem. J Nutr Health Aging. 2020;24(3):243-245. doi: 10.1007/s12603-020-1323-6. PMID: 32115602; PMCID: PMC7223173.
[3] Zhang, K., Yuan, H., & Fang, Y. (2022, October). Evaluation of smart agitation prediction and management for dementia care and novel universal village-oriented solution for integration, resilience, inclusiveness and sustainability. In 2022 6th International Conference on Universal Village (UV) (pp. 1-34). IEEE.
[4] Zhang, L., Ren, J., Yuan, H., et al. (2020).Evaluation of Smart Healthcare Systems and Novel UV-Oriented Solution for Integration, Resilience, Inclusiveness and Sustainability.In:Proceedings of the 2020 5th International Conference on Universal Village (UV), 24–27 October 2020, Boston, NY: IEEE, pp. 1–28.
[5] Alessa, A., & Al-Khalifa, H. (2023).Towards Designing a ChatGPT Conversational Companion for Elderly People. arXiv preprint arXiv:2304.09866.
[6] Chutia, T., & Baruah, N. (2024). A review on emotion detection by using deep learning techniques. Artificial Intelligence Review, 57(8), 203.
[7] Abdollahi, H., Mahoor, M. H., … (2022).Artificial Emotional Intelligence in Socially Assistive Robots for Older Adults: A Pilot Study.arXiv preprint arXiv:2201.11167.
[8] Tonmoy, S. M. I., Zaman, S. M. M., Jain, V., Rani, A., Rawte, V., Chadha, A., & Das, A. (2023).A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models.arXiv preprint.
[9] Zhou, Y., Li, X., & Zhang, L. (2025). Hallucination mitigation for retrieval- augmented large language models: A review. Applied Sciences, 15(5), 856.
[10] Khalil, R. A., & Amin, S. (2025). Deep learning-based facial expression recognition for the elderly. arXiv preprint arXiv:2502.02618.
[11] Khalil, R. A., Amin, S., & Smith, J. (2025). Redefining elderly care with agentic AI: Challenges and opportunities. arXiv preprint arXiv:2507.14912.
[12] Yuan, R., Sun, S., Li, Y., Wang, Z., Cao, Z., & Li, W. (2023). Personalized large language model assistant with evolving conditional memory. arXiv preprint arXiv:2312.17257.
[13] Dennis Jacob, Hend Alzahrani, Zhanhao Hu, Basel Alomair, and David Wagner. 2025. PromptShield: Deployable Detection for Prompt Injection Attacks. In Proceedings of the Fifteenth ACM Conference on Data and Application Security and Privacy (CODASPY '25). Association for Computing Machinery, New York, NY, USA, 341–352. https://doi.org/10.1145/3714393.3726501
[14] Sun, X., Liu, G., He, Z., Li, H., & Li, X. (2024). Deprompt: Desensitization and evaluation of personal identifiable information in large language model prompts. arXiv preprint arXiv:2408.08930.
[15] Priyanshu, A., Vijay, S., Kumar, A., Naidu, R., & Mireshghallah, F. (2023). Are chatbots ready for privacy-sensitive applications? an investigation into input regurgitation and prompt-induced sanitization. arXiv preprint arXiv:2305.15008.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 by author(s) and Erytis Publishing Limited.
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
