好色先生TV

Psychologists have long known that social situations profoundly influence human behavior, yet have lacked a unified, empirically grounded way to describe them. A new study addresses this problem by using generative AI to systematically classify thousands of everyday social interactions. In a new study, researchers analyzed thousands of textual descriptions of two-person social interactions, then used generative artificial intelligence (AI) to code the exchanges by features, resulting in a taxonomy of categories of social interactions. Then they related these groups to variables like conflict, power, and duty to provide a comprehensive, data-driven framework for quantifying the structure of interactions.

The study, 鈥淭he Structure of Social Situations: Insights From the Large-Scale Automated Coding of Text,鈥� by researchers at 好色先生TV and the University of Pennsylvania (Penn), is published in Psychological Science. 鈥淩esearchers have proposed many frameworks for representing social situations, but due to the diversity and complexity of real-life situations, many of these are partial, non-integrated, and not mapped onto situations encountered in everyday life,鈥� says Taya R. Cohen, Professor of Organizational Behavior and Business Ethics at Carnegie Mellon鈥檚 Tepper School of Business, who coauthored the study. 鈥淥ur work advances the study of social cognition and behavior by using AI to create a more comprehensive framework for the structure of social situations.鈥�

Because social situations exert a profound influence on human behavior and mental life, understanding the structure and dimensions of such situations has been a major topic of psychology research for decades. But gaps remain, leaving the field without a rigorous understanding of how the characteristics that matter most relate to commonly encountered social interactions.

In this study, researchers analyzed more than 20,000 detailed textual descriptions of two-person social interactions. They used a large data set of short stories describing social interactions in daily life (e.g., family situations, workplace interactions, animal interactions, pet mishaps written by online participants, as well as short situational descriptions from other sources (e.g., blogs, novels, fiction published on social media, reading-comprehension exams).

The study used a combination of large language model (LLM) techniques to extract high-level situational characteristics from the data sets and core situational cues like relationships, activities, locations, and goals (who, what, where, and why) that make up the observable dimensions of each situation.
鈥淎 core challenge in psychology is understanding the structure of social situations鈥攖he patterns and psychological features that shape how people think, feel, and behave in social contexts,鈥� explains Sudeep Bhatia, Associate Professor of Psychology at Penn, who led the study. 鈥淥ur work provides a rigorous and integrative framework for mapping out everyday social situations and relating them to key theoretical dimensions in psychology.鈥澛�

The study found systematic associations between situational characteristics proposed by existing taxonomies as well as between situational characteristics and observable cues, replicating and extending findings from earlier studies, but at a much larger scale. In particular, the study drew on a broader and more representative group of typical exchanges experienced by adults.

鈥淥ur study offers researchers a rich descriptive catalogue of dozens of classes of situations with which they can test and refine their theories,鈥� Bhatia added, 鈥淚t can be used to model the distributional structure of situations, as we did, as well as to formally study the effect of situations on interpersonal behavior, perceptions of situations, pursuit of goals, and the interplay between situations and personality.鈥�

Among the study鈥檚 limitations, the authors note that their analysis relied on short stories, which resemble the brief autobiographical narratives used in prior research but likely exclude more complex and nuanced situations. In addition, their findings depended on analyses conducted with current-generation LLMs, which have biases and constraints. Finally, the work examined only English-language narratives, which limits the cultural scope of the conclusions.

###

Bhatia, S., Yang, A., & Cohen, T. R. (2026). The Structure of Social Situations: Insights From the Large-Scale Automated Coding of Text. Psychological Science, 0(0).