Tweetorial Hooks: Generative AI Tools to Motivate Science on Social Media
This addresses the problem of public engagement in science communication for STEM experts, but it is incremental as it applies existing LLM methods to a specific writing task.
The paper tackles the challenge of STEM experts struggling to write engaging opening tweets (hooks) for science communication on social media by using large language models (LLMs) to help scaffold the writing process, resulting in reduced cognitive load and improved hook quality.
Communicating science and technology is essential for the public to understand and engage in a rapidly changing world. Tweetorials are an emerging phenomenon where experts explain STEM topics on social media in creative and engaging ways. However, STEM experts struggle to write an engaging "hook" in the first tweet that captures the reader's attention. We propose methods to use large language models (LLMs) to help users scaffold their process of writing a relatable hook for complex scientific topics. We demonstrate that LLMs can help writers find everyday experiences that are relatable and interesting to the public, avoid jargon, and spark curiosity. Our evaluation shows that the system reduces cognitive load and helps people write better hooks. Lastly, we discuss the importance of interactivity with LLMs to preserve the correctness, effectiveness, and authenticity of the writing.