arXiv subjects

In Song Kim

Publications and source records attributed to In Song Kim.

4 recordsLinked to original sources

arXiv2025

Measuring Interest Group Positions on Legislation: An AI-Driven Analysis of Lobbying Reports

Special interest groups (SIGs) in the U.S. participate in a range of political activities, such as lobbying and making campaign donations, to influence policy decisions in the legislative and executive branches. The competing interests of these SIGs have profound implications for global issues such as international trade policies, immigration, climate change, and global health challenges. Despite the significance of understanding SIGs' policy positions, empirical challenges in observing them have often led researchers to rely on indirect measurements or focus on a select few SIGs that publicly support or oppose a limited range of legislation. This study introduces the first large-scale effort to directly measure and predict a wide range of bill positions-Support, Oppose, Engage (Amend and Monitor)- across all legislative bills introduced from the 111th to the 117th Congresses. We leverage an advanced AI framework, including large language models (LLMs) and graph neural networks (GNNs), to develop a scalable pipeline that automatically extracts these positions from lobbying activities, resulting in a dataset of 42k bills annotated with 279k bill positions of 12k SIGs. With this large-scale dataset, we reveal (i) a strong correlation between a bill's progression through legislative process stages and the positions taken by interest groups, (ii) a significant relationship between firm size and lobbying positions, (iii) notable distinctions in lobbying position distribution based on bill subject, and (iv) heterogeneity in the distribution of policy preferences across industries. We introduce a novel framework for examining lobbying strategies and offer opportunities to explore how interest groups shape the political landscape.

cs.CY↗

arXiv2025

Measuring the dynamical evolution of the United States lobbying network

Lobbying networks constitute complex political systems that mobilize vast human and financial resources to influence governmental decision-making, often with profound national and global consequences. A comprehensive understanding of lobbying strategies and dynamics requires time-resolved, system-wide data, which are largely unavailable for most political systems. In the United States (U.S.), the Lobbying Disclosure Act (LDA) of 1995 mandates public reporting of all federal lobbying activities in detailed quarterly filings. However, extracting structured, quantitative information from these filings has remained technically challenging and labor-intensive. Here we present and analyze LobbyView, a relational database that integrates and disambiguates data from more than 1.6 million LDA reports. LobbyView provides access to detailed lobbying disclosures, reconciled corporate entities, and tools for linking LDA data to external legislative and corporate databases. We demonstrate the utility of LobbyView by examining both macro-level and highly granular lobbying dynamics. Specifically, we reconstruct the connectivity patterns of the U.S. lobbying network, and we show how they evolve over time, we identify organizational principles such as the accumulation of professional contacts within a small set of firms, and reveal how lobbying activity is synchronized with electoral cycles. Moreover, we introduce a probabilistic framework for analyzing lobbying behavior at the scale of individual bills, issues, or firms. We envision LobbyView as a resource not only for political scientists, but also for quantitative interdisciplinary research, enabling the application of methods from statistical physics, systems biology, and machine learning to the study of lobbying systems.

physics.soc-ph↗

arXiv2025

PanelMatch: Matching Methods for Causal Inference with Time-Series Cross-Section Data

Analyzing time-series cross-sectional (also known as longitudinal or panel) data is an important process across a number of fields, including the social sciences, economics, finance, and medicine. PanelMatch is an R package that implements a set of tools enabling researchers to apply matching methods for causal inference with time-series cross-sectional data. Relative to other commonly used methods for longitudinal analyses, like regression with fixed effects, the matching-based approach implemented in PanelMatch makes fewer parametric assumptions and offers more diagnostics. In this paper, we discuss the PanelMatch package, showing users a recommended pipeline for doing causal inference analysis with it and highlighting useful diagnostic and visualization tools.

stat.ME↗

arXiv2021

Learning Bill Similarity with Annotated and Augmented Corpora of Bills

Bill writing is a critical element of representative democracy. However, it is often overlooked that most legislative bills are derived, or even directly copied, from other bills. Despite the significance of bill-to-bill linkages for understanding the legislative process, existing approaches fail to address semantic similarities across bills, let alone reordering or paraphrasing which are prevalent in legal document writing. In this paper, we overcome these limitations by proposing a 5-class classification task that closely reflects the nature of the bill generation process. In doing so, we construct a human-labeled dataset of 4,721 bill-to-bill relationships at the subsection-level and release this annotated dataset to the research community. To augment the dataset, we generate synthetic data with varying degrees of similarity, mimicking the complex bill writing process. We use BERT variants and apply multi-stage training, sequentially fine-tuning our models with synthetic and human-labeled datasets. We find that the predictive performance significantly improves when training with both human-labeled and synthetic data. Finally, we apply our trained model to infer section- and bill-level similarities. Our analysis shows that the proposed methodology successfully captures the similarities across legal documents at various levels of aggregation.

cs.CL↗