🤖 AI Summary
Existing studies predominantly extract features directly from narrative content to predict user engagement, neglecting the modeling of audience forward-looking expectations—i.e., readers’ beliefs about future story developments. This work introduces the first generative framework grounded in large language models (LLMs), which explicitly characterizes prospective psychological variables—including reader expectations, uncertainty, and surprise—via multi-path narrative continuation. These variables are systematically integrated into engagement prediction. To our knowledge, this is the first approach enabling computationally tractable modeling of forward-looking beliefs over unstructured narrative data. Evaluated on over 30,000 novel chapters, the method achieves an average 31% gain in marginal explanatory power over conventional feature engineering, significantly improving predictive performance across diverse engagement behaviors—including reading duration, commenting, and voting.
📝 Abstract
Understanding when and why consumers engage with stories is crucial for content creators and platforms. While existing theories suggest that audience beliefs of what is going to happen should play an important role in engagement decisions, empirical work has mostly focused on developing techniques to directly extract features from actual content, rather than capturing forward-looking beliefs, due to the lack of a principled way to model such beliefs in unstructured narrative data. To complement existing feature extraction techniques, this paper introduces a novel framework that leverages large language models to model audience forward-looking beliefs about how stories might unfold. Our method generates multiple potential continuations for each story and extracts features related to expectations, uncertainty, and surprise using established content analysis techniques. Applying our method to over 30,000 book chapters, we demonstrate that our framework complements existing feature engineering techniques by amplifying their marginal explanatory power on average by 31%. The results reveal that different types of engagement-continuing to read, commenting, and voting-are driven by distinct combinations of current and anticipated content features. Our framework provides a novel way to study and explore how audience forward-looking beliefs shape their engagement with narrative media, with implications for marketing strategy in content-focused industries.