Abstract: A brand’s slogan is one of the major components of a brand’s identity, builds brand awareness,and increases brand recognition. Previous work has evaluated the effect of a small number of predefined semantic and linguistic features on slogan likeability and memorability. We propose to develop and validate a model that uses automatically extracted, high-dimensional sentence embeddings to predict the likeability and memorability of new and existing slogans. We will visualize the semantic information in our model by applying it to established lexicons, and validate it in empirical studies with lay people and marketing managers. Our model will facilitate the generation of slogans by marketers, and provide new insight into slogan effectiveness for marketing science.