The ideological orientation of academic social science research 1960–2024
https://link.springer.com/article/10.1007/s11186-026-09690-2
I cannot say much about the text analysis that is LLM-based, but some thoughts on other elements of the analysis:
a) Analyzing ideological stance of abstracts from 1960-2024 against a US 2025 ideological spectrum 1/
The ideological orientation of academic social science research 1960–2024 - Theory and Society

This study analyzes approximately 600,000 English-language social science abstracts published between 1960 and 2024 to estimate the long-run ideological orientation of disciplinary research output. Large language models (LLMs) were applied to each abstract using a fixed 2025 U.S. ideological spectrum, enabling consistent coding across six decades. Five key findings emerged. First, roughly 90 percent of politically relevant social science articles leaned left 1960–2024, and the mean political stance of every social science discipline was left-of-center every year during the period. Second, all disciplines showed leftward movement between 1990 and 2024. Third, policy-proximal disciplines generally showed limited rightward moderation between roughly 1970 and 1990, though policy-distal disciplines did not. Fourth, disciplines with greater leftward orientation generally displayed greater ideological homogeneity Fifth, sociocultural content was more consistently left-leaning than economic content, and that gap widened over time. Robustness checks using a wide assortment of alternative datasets and analytical methodologies indicated that these findings were unlikely to be artifacts of idiosyncratic assumptions. Methodologically, the study demonstrates the capacity of LLM-based text classification to deliver reliable, large-scale ideological measurement over time, a task previously impractical with human coding alone. Taken together, the analysis provides the first systematic, cross-disciplinary evidence of the long-run political orientation of anglophone social science scholarship, revealing both the persistence and the intensification of its leftward tendencies, particularly in sociocultural domains.

SpringerLink
is not convincing to me. This is discussed in the article, but I think abstracts should be compared to ideology at the time, which would be harder to study. From the top of my head, I'd say it is not surprising that most abstracts are coded as left against a 2025 ideological reference point, and that the share would be smaller if compared to earlier years.
b) It looks like it's not filtered for authors in/from US. I don't see why research from non-US authors should be compared to US ideology. 2/
c) Methodologically, the article states several times "To minimize researcher degrees of freedom" in relation with the use of an LLM and prompting. This seems to miss the point because the prompting is the main degree of freedom in this analysis. 3/