'I Will Follow You!' – How Recommendation Modality Impacts Processing Fluency and Purchase Intention

Although conversational agents (CA) are increasingly used for providing purchase recommendations, important design questions remain. Across two experiments we examine with a novel fluency mechanism how recommendation modality (speech vs. text) shapes recommendation evaluation (persuasiveness and risk), the intention to follow the recommendation, and how modality interacts with the style of recommendation explanation (verbal vs. numerical). Findings provide robust evidence that text-based CAs outperform speech-based CAs in terms of processing fluency and consumer responses. They show that numerical explanations increase processing fluency and purchase intention of both recommendation modalities. The results underline the importance of processing fluency for the decision to follow a recommendation and highlight that processing fluency can be actively shaped through design decisions in terms of implementing the right modality and aligning it with the optimal explanation style. For practice, we offer actionable implications on how to make effective sales agents out of CAs.