Social scientists commonly seek to make statements about how word use varies over circumstances—including time, partisan identity, or some other document-level covariate. For example, researchers might wish to know how Republicans and Democrats diverge in their understanding of the term “immigration.” Building on the success of pretrained language models, we introduce the à la carte on text (conText) embedding regression model for this purpose. This fast and simple method produces valid vector representations of how words are used—and thus what words “mean”—in different contexts. We show that it outperforms slower, more complicated alternatives and works well even with very few documents. The model also allows for hypothesis testing and statements about statistical significance. We demonstrate that it can be used for a broad range of important tasks, including understanding US polarization, historical legislative development, and sentiment detection. We provide open-source software for fitting the model.

Despite social scientists’ long-standing interest in the influences of siblings, previous research has not settled the debates on how relevant sibship size is to child development and whether growing up with more siblings could be beneficial. Using 30 years of longitudinal data and fixed-effects models, this study offers the most comprehensive evidence on how sibship size is tied to cognitive and sociobehavioral development. We also advance the literature by systematically comparing the consequences of gaining a sibling for children with varying ordinal positions. Contrary to prior studies using selective data from limited observation spans, we find that children experience net decreases in cognitive test scores as their family size grows. At the same time, our analysis shows that sibling additions are only important to first- and second-born children’s—not later-born children’s—cognitive development. Even for the first- and second-born, the marginal effect of adding a sibling lessens with each addition. Our results thus demonstrate the time-dependent nature of family resource-dilution processes. For sociobehavioral development, the evidence indicates that having an older sibling is beneficial, but gaining a younger sibling increases behavioral problems for some (e.g., first-born children). Because more children from large families have older siblings, children from larger families exhibit less problematic behavior, on average. By uncovering the complex relationship between siblings and noncognitive development, this study also generally contributes to the sociology of family and inequality.