This capstone investigates how generative AI can produce emotionally intelligent content that aligns with both brand voice and audience personality traits. We develop a controllable generative model that tailors copy to specific personality types by fine-tuning a large language model on scripts from four iconic film characters, enabling the system to emulate each character’s tone, vocabulary, and sentence patterns while preserving the original message. The resulting model delivers [insert key performance metrics—e.g., style adherence, meaning preservation, toxicity/brand-safety scores], and outperforms baseline generation on [insert benchmarks or comparisons]. In evaluation, our approach [insert results—e.g., “increased perceived emotional resonance by X% and brand consistency by Y%”] across targeted segments. These findings demonstrate that personality-aligned generation can measurably enhance engagement and brand coherence, offering a scalable path to personalized marketing at lower content production cost and faster velocity.
Watch the team present this project at 01:43:55 in the session recording here.
Keywords: Generative AI, brand voice, personality modeling, NLP, fine-tuning, tone analysis
Faculty Advisor
Anil Chaturvedi has over 35 years of professional experience at companies such as AT&T Bell Labs, Kraft Foods, Capital One, and Accenture. He has provided consulting services to Bank of America, Fannie Mae, Johnson & Johnson, and Procter & Gamble. His general research interests include enhancing business value using data science. He has patented and published advanced algorithms for predictive modeling, market segmentation, new product development, product positioning, customer loyalty, consumer promotion mix optimization, and brand strategy. He earned his PhD from Rutgers University and an MBA from IIM Ahmedabad, India.