The authors provide a framework to evaluate codebook-LLM measurement, classifying unlabeled documents with LLMs given a human-written codebook. Ultimately, supervised instruction-tuning can substantially improve performance. Read the full paper here: www.cambridge.org/core/journal...

Bipartite networks are common in social science, but researchers often project data on unipartite networks for analysis. This new model uncovers patterns across node types, uses covariates to explain ties, and fits efficiently. Read the full paper here: www.cambridge.org/core/journal...

GNNs are advantageous because they can be trained, saved, and deployed on new data, and they can also generate synthetic data. The paper uses the militarized international disputes dataset to illustrate potential applications. Read the paper here: www.cambridge.org/core/journal...

The package is demonstrated using several political examples where researchers may wish to join messy data. The fuzzylink package outperforms existing methods and even allows researchers to link datasets across languages. You can read the full paper here: www.cambridge.org/core/journal...

The authors apply the SIR model to data on monthly conflict events between countries, highlighting the model’s ability to illustrate complex influence patterns within networks by linking them to specific covariates. You can read the full paper here: www.cambridge.org/core/journal...

Using House procedural vs final passage votes, the model shows that minority-party members and legislators from moderate constituencies are most likely to shift positions across domains. You can read the full paper here: www.cambridge.org/core/journal...

This is validated using Arabic-language media published during the Arab Spring. Existing expert-based indices perform less well in stable autocracies, failing to detect short-term or subtle variations in media criticism. You can read the full paper here: www.cambridge.org/core/journal...

The advantages are validated on a set of appellate decisions. These ideology estimates predict outcomes more accurately than existing appellate measures, and can inform debates on the nature of judicial ideology and decision-making. You can read the full paper here: www.cambridge.org/core/journal...

The authors replicate a study on parties’ use of moral foundations and show how different measurements can lead to opposite effect directions. They also offer best practices for studying moral foundations in political texts. Read the full paper here: www.cambridge.org/core/journal...

The method is demonstrated by extracting agenda items from city council meeting minutes. This workflow can accurately extract subsections of text from a document and required only a few hand labeled documents to train. You can read the full paper here: www.cambridge.org/core/journal...

They use BCCP to forecast fatalities from armed conflicts and demonstrate that it provides well-calibrated uncertainty estimates. The authors also provide guidance and an R package for the BCCP algorithm. You can read the paper here: www.cambridge.org/core/journal...

The authors replicate existing experiments and find that precision gains from block-randomized or pre-post designs can withstand sample loss that may arise during implementation. You can read the full paper here: www.cambridge.org/core/journal...

The CPW estimator is demonstrated using a replication of a survey experiment, and shows stronger treatment effects than previously found. This suggests that meaningful effects can be missed using alternative approaches. You can read the full paper here: www.cambridge.org/core/journal...