Automatic Generation of Custom Advertisement Messages based on Literacy Styles of Classified Personality Types

Jimin Seong, Yunjong Choi, Doyeon Kwak, Hansaem Kim

http://doi.org/10.5626/JOK.2024.51.1.23

This study introduces a novel framework that defines marketing styles based on the MBTI personality types, and presents a machine learning technique to generate customized advertising messages aligned to these types. We use the BART algorithm to synthesize customized advertising content by training on the advertisement texts incorporating personality type prefixes. Our experiments confirm the model’s efficacy in transforming generic advertising copy into custom messages that embody the distinct style characteristics of each personality type, via prefix manipulation. Theoretically, our research establishes the relationship between style characteristics and personality types; practically, it provides the technique to fine-tune a language model to generate advertising messages that align with specific personality types. Moreover, this research serves as a foundational work for systematizing and replicating stylistic differences across various languages and regions.