Date of Award

6-18-2025

Document Type

Thesis

Publisher

Santa Clara : Santa Clara University, 2025

Department

Computer Science and Engineering

First Advisor

Yi Fang

Second Advisor

Oana Ignat

Abstract

Personal inspiration and motivation are fundamental drivers of well-being and growth, yet current digital wellness solutions predominantly reflect Western perspectives, failing to address the diverse cultural contexts through which inspiration manifests globally. This thesis presents the development of an Inspirational Coach platform that leverages artificial intelligence to deliver culturally-adaptive personal development content. The system employs a fine-tuned Llama 3.1 8B model using Low-Rank Adaptation (LoRA) techniques to generate personalized motivational content that incorporates users’ cultural backgrounds, personal themes, and individual preferences.

The platform integrates four core features within a comprehensive React-based web application: guided journaling with mood tracking, goal setting and progress monitoring, culturally-adapted daily affirmations, and AI-generated personalized inspirational content. The system architecture combines a Next.js frontend with Firebase for real-time data management and user authentication, while a FastAPI server hosts the fine-tuned language model for content generation. Extensive user research informed the design process, ensuring cultural sensitivity and accessibility across diverse demographic groups.

Evaluation results demonstrate the platform’s e↵ectiveness in delivering culturally-relevant inspirational content. The fine-tuned model successfully adapts content to incorporate cultural wisdom, proverbs, and perspectives while maintaining authenticity and avoiding stereotypical representations. This work contributes to the emerging field of culturally-inclusive AI applications and establishes a framework for responsible development of AI-powered personal development tools that respect and celebrate cultural diversity.

Download

Share

COinS