Can AI Outperform Human Experts in Creating Social Media Creatives?
Eunkyung Park, Raymond K. Wong, Junbum Kwon
TL;DR
This work investigates whether AI can surpass human experts in creating social media creatives by introducing a Prompt-for-Prompt framework that uses GPT-4 to augment human text descriptions for state-of-the-art text-to-image generators (Midjourney, DALL-E 3, Stable Diffusion). Using top-brand Instagram posts as the source material, the study shows AI-generated creatives achieve higher engagement than human-generated ones, with Midjourney performing best and natural-style prompts outperforming eye-catching prompts. The analysis reveals AI gains are largest for animal and product imagery and when descriptions are short, while prompts are less effective for people-centered content. The findings support the practical adoption of LLM-driven prompt augmentation to enhance creative outputs in social media campaigns and provide a nuanced view of when AI-assisted creativity offers the most benefit.
Abstract
Artificial Intelligence has outperformed human experts in functional tasks such as chess and baduk. How about creative tasks? This paper evaluates AI's capability in the creative domain compared to human experts, which little research has been conducted so far. We propose a novel Prompt-for-Prompt to generate social media creatives via prompt augmentation by Large Language Models. We take the most popular Instagram posts (with the biggest number of like clicks) in top brands' Instagram accounts to create social media creatives. We give GPT 4 several prompt instructions with text descriptions to generate the most effective prompts for cutting-edge text-to-image generators: Midjourney, DALL E 3, and Stable Diffusion. LLM-augmented prompts can boost AI's abilities by adding objectives, engagement strategy, lighting and brand consistency for social media image creation. We conduct an extensive human evaluation experiment, and find that AI excels human experts, and Midjourney is better than the other text-to-image generators. Surprisingly, unlike conventional wisdom in the social media industry, prompt instruction including eye-catching shows much poorer performance than those including natural. Regarding the type of creatives, AI improves creatives with animals or products but less with real people. Also, AI improves creatives with short text descriptions more than with long text descriptions, because there is more room for AI to augment prompts with shorter descriptions.