Summary of Modeling Story Expectations to Understand Engagement: a Generative Framework Using Llms, by Hortense Fong and George Gui
Modeling Story Expectations to Understand Engagement: A Generative Framework Using LLMs
by Hortense Fong, George Gui
First submitted to arxiv on: 13 Dec 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); General Economics (econ.GN); Methodology (stat.ME)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper introduces a novel framework that uses large language models to model audience forward-looking beliefs about how stories might unfold. The method generates multiple potential continuations for each story and extracts features related to expectations, uncertainty, and surprise using established content analysis techniques. The authors apply their method to over 30,000 book chapters from Wattpad and demonstrate that it complements existing feature engineering techniques by amplifying their marginal explanatory power on average by 31%. The results show that different types of engagement-continuing to read, commenting, and voting-are driven by distinct combinations of current and anticipated content features. This framework provides a novel way to study how audience forward-looking beliefs shape their engagement with narrative media. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about understanding why people engage with stories. It’s important for content creators and platforms because it helps them make better decisions. Right now, there are some theories that say how people believe a story will end affects whether they keep reading or not. But no one has developed a good way to measure this until now. This paper introduces a new method using big language models to predict what readers think will happen next in a story. The researchers tested it on over 30,000 chapters from a popular book-sharing platform and found that it works really well. It can even help explain why people do different things when they read a story- like keep reading, commenting, or voting. |
Keywords
» Artificial intelligence » Feature engineering
