A probabilistic model of hype reveals a rhetorical shift in biomedicine

Abstract Promotional language, or “hype,” characterized by words like novel, outstanding, and promising, has been increasingly observed in scientific writing. To systematically analyze how hype is employed and evolves in structured biomedical abstracts, we introduce a probabilistic model to estimate the propensity of hype in selected candidate words in biomedical abstracts. Our analysis examines the positional distribution of 43 candidate hype words across approximately 14.5 million PubMed abstracts within the IMRaD (Introduction, Methods, Results, and Discussion) framework of structured writing. The model accounts for context, filtering out technical concepts (e.g., major histocompatibility complex or vital capacity) and nonhyping uses (e.g., outstanding questions). We find that the degree of hype varies depending on the word and its context: Words such as promising and noteworthy frequently convey hype, whereas others, like major and central, typically remain neutral. Temporal trends suggest that the increased hype is not due to a shift in the words' propensity to hype but rather authors' strategic rhetorical choices, particularly in the Introduction and Discussion sections. This analytical approach enhances the identification and understanding of hype's role, and we provide a labeled data set annotated with abstract-level hype probabilities to facilitate further research into its impact on scientific communication.