Lindsay E. Young | Searcharxiv

arXiv2026

The Body as Status: Muscularity, Engagement, and Body Image Risk on #GymTok

Body image concerns among boys and young men are increasingly oriented toward muscularity, with social media serving as a central context for communicating and evaluating these ideals. While prior research has focused on the thin-ideal, less is known about how the muscular-ideal is represented and reinforced on visual social media platforms. This study examines (1) dominant content themes, (2) perceived harm to body image, and (3) engagement patterns across #GymTok, a muscularity-oriented fitness subculture on TikTok. We conducted a content analysis of 2,210 #GymTok videos annotated by clinical experts across themes like self-objectification, rigid dieting, excessive exercise, supplement and steroid use, and masculinity. Annotators also rated the perceived harm of videos to the viewers' body image, and depicted bodies were coded according to muscularity level. Perceived harm varied across content themes, with supplement- and steroid-related content rated as most harmful. Engagement was positively associated with both muscularity and perceived harm: videos depicting more muscular bodies and those rated as more harmful received greater views, likes, shares, and comments. Although less prevalent, masculinity-focused content generated the highest engagement. These findings suggest that TikTok may not only expose users to muscular ideals and potentially harmful behaviors, but also algorithmically amplify them. By increasing the visibility of highly muscular and harmful content, recommendation systems may intensify social comparison processes, while objectification elevates the muscular body into a marker of status, masculinity, and social worth. Together, these dynamics may contribute to body image risk among boys and young men.

cs.CY↗

arXiv2026

Overstating Attitudes, Ignoring Networks: LLM Biases in Simulating Misinformation Susceptibility

Large language models (LLMs) are increasingly used as proxies for human judgment in computational social science, yet their ability to reproduce patterns of susceptibility to misinformation remains unclear. We test whether LLM-simulated survey respondents, prompted with participant profiles drawn from social survey data measuring network, demographic, attitudinal and behavioral features, can reproduce human patterns of misinformation belief and sharing. Using three online surveys as baselines, we evaluate whether LLM outputs match observed response distributions and recover feature-outcome associations present in the original survey data. LLM-generated responses capture broad distributional tendencies and show modest correlation with human responses, but consistently overstate the association between belief and sharing. Linear models fit to simulated responses exhibit substantially higher explained variance and place disproportionate weight on attitudinal and behavioral features, while largely ignoring personal network characteristics, relative to models fit to human responses. Analyses of model-generated reasoning and LLM training data suggest that these distortions reflect systematic biases in how misinformation-related concepts are represented. Our findings suggest that LLM-based survey simulations are better suited for diagnosing systematic divergences from human judgment than for substituting it.

cs.SI↗