MoodSmith: Enabling Mood-Consistent Multimedia for AI-Generated Advocacy Campaigns
Samia Menon, Sitong Wang, Lydia Chilton
TL;DR
MoodSmith presents a three-stage AI-powered workflow that enables nonprofits to create short advocacy videos with mood-consistency across script, visuals, and audio. By leveraging emotive scripting with GPT-4, mood-driven visual generation via Stable Diffusion, and Spotify/TikTok-based music selection, the system supports exploration of diverse moods while maintaining cross-modal coherence. Technical and user studies show MoodSmith improves mood accuracy, cross-channel consistency, and clarity compared with a baseline workflow, and users report ease of mood exploration and actionable insights for future improvements. The work advances mood-aware content creation in nonprofit outreach, offering a practical, human-centered tool that democratizes production of persuasive PSAs and informs future research on adaptive interfaces and mood-aware media generation.
Abstract
Emotion is vital to information and message processing, playing a key role in attitude formation. Consequently, creating a mood that evokes an emotional response is essential to any compelling piece of outreach communication. Many nonprofits and charities, despite having established messages, face challenges in creating advocacy campaign videos for social media. It requires significant creative and cognitive efforts to ensure that videos achieve the desired mood across multiple dimensions: script, visuals, and audio. We introduce MoodSmith, an AI-powered system that helps users explore mood possibilities for their message and create advocacy campaigns that are mood-consistent across dimensions. To achieve this, MoodSmith uses emotive language and plotlines for scripts, artistic style and color palette for visuals, and positivity and energy for audio. Our studies show that MoodSmith can effectively achieve a variety of moods, and the produced videos are consistent across media dimensions.