Jong Hee Park

  • is Professor in the Dept. of Political Science and International Relations at Seoul National University,
  • is Director of Global Data Cener at Institute of International Studies, Seoul National University,
  • studies political methodology and international political economy,
  • received Ph.D. from Washington University in St. Louis,
  • maintains MCMCpack and Bayesian taskview in CRAN,
  • , and is recently working on dynamic network analysis, text analysis of North Korean document, and changepoint anlaysis of Bayesian shrinkage models

Detecting Structural Changes in Longitudinal Network Data

Dynamic modeling of longitudinal networks has been an increasingly important topic in applied research. While longitudinal network data commonly exhibit dramatic changes in its structures, existing methods have largely focused on modeling smooth topological changes over time. In this paper, we develop a hidden Markov multilinear tensor model (HMTM) that combines the multilinear tensor regression model (Hoff 2011) with a hidden Markov model using Bayesian inference. We model changes in network structure as shifts in discrete states yielding particular sets of network generating parameters. Our simulation results demonstrate that the proposed method correctly detects the number, locations, and types of changes in latent node characteristics. We apply the proposed method to international military alliance networks to find structural changes in the coalition structure among nations.

Learn More (Paper) Learn More (Slide)

Key Figure Dynamic Network Analysis using News Articles

In this paper, we present a method for analyzing a dynamic network of key figures in the U.S.-North Korea relations during the first two quarters of 2018. Our method constructs key figure networks from U.S. news articles on North Korean issues by taking co-occurrence of people’s names in an article as a domain-relevant social link. We call a group of people that co-occur repeatedly in the same domain (news articles on North Korean issues in our case) “key figures” and their social networks “key figure networks.” We analyze block-structure changes of key figure networks in the U.S.-North Korea relations using a Bayesian hidden Markov multilinear tensor model. The results of our analysis show that block structure changes in the key figure network in the U.S.-North Korea relations predict important game- changing moments in the U.S.-North Korea relations in the first two quarters of 2018.

Learn More (Paper) Slide (Korean)

Bayesian Regularized Regression with Change-points: High-dimensional Longitudinal Analysis in Social Sciences

Recent innovations in regularization methods offer an important breakthrough to regression analysis with many predictors. However, existing regularization methods commonly assume that the level of sparsity or shrinkage does not change given observed data. This assumption is often problematic in the presence of time-varying effects in longitudinal data because regularizing time-varying parameters toward zero leads to erroneous inferential results. In this paper, we present a statistical method that allows both regularization and estimation of parameter changes in high dimensional longi- tudinal data. The proposed method, which we call hidden Markov Bayesian bridge model (HMBB), uses Polson, Scott and Windle (2014)’s Bayesian bridge model for parameter regularization and a hidden Markov model to estimate parameter changes. Simulation studies show that the HMBB outperforms other regularization methods in recovering time-varying parameters as well as time-constant parameters in various settings. We apply the HMBB to Nunn and Qian (2014)’s study of the effect of U.S. food aid on civil conflicts and report new findings.

Learn More (Paper) Learn More (Slide)

Multilayer Network Analysis

Network scholars commonly encounter multiple networks, each of which is possibly governed by distinct generation rules while sharing a node group structure. Although the stochastic blockmodeling—detecting such latent group structures with group-specific connection pro- files—has been a major topic of recent research, the focus has been given to the assortative group discovery of a single network. Despite its universality, concepts, and techniques for simultaneous characterization of node traits of multilayer networks, constructed by stacking multiple networks into layers, have been limited. Here, we propose a Bayesian multilayer stochastic blockmodeling framework that uncovers layer-common node traits and factors associated with layer-specific network generating functions. Without assuming a priori layer- specific generation rules, our fully Bayesian treatment allows probabilistic inference of latent traits. We extend the approach to detect changes in block structures embedded in temporal layers of network time series. We demonstrate the method using synthetic multilayer networks with assortative, disassortative, core-periphery, and overlapping community structures. Finally, we apply the method to empirical social network datasets, and find that it detects significant latent traits and structural changepoints. In particular, we uncover endogenous historical regimes associated with distinct constellations of states in United States Senate roll call vote similarity patterns.

Learn More (Paper)

세월호 참사 언론보도의 정치적 경도

본 논문은 세월호 참사와 관련된 1년 동안의 언론보도를 이용하여 여론의 흐름과 언론매체의 정치적 경도(partisan slant)를 측정하는 것을 목적으로 한다. 본 논문은 자동화된 텍스트 분석기법과 베이지안 추정을 결합하여 28개 언론매체(19개 신문사와 9개의 방송사)의 보도내용을 분석하였다. 이를 통해 세월호 참사 1년 동안 언론보도를 통해 드러난 여론의 흐름이 급격한 변화를 보였으며 참사 초기의 정부비판적 여론이 대통령의 대국민 담화와 두 번의 선거(6.4 지방선거와 7.30 재보궐선거)를 거치면서 급격하게 약화되었음을 확인할 수 있었다.

세월호 참사 언론보도 연구 페이지로 이동

Quality Over Quantity: A Lineage-Survival Strategy of Elite Families in Pre-Modern Korea

In this paper, we study social mobility across multiple generations in pre-modern Korea. Using two extant oldest family records, jokbo, we construct a prospective genealogical microdata containing the entire records of public offices and reproduction over five generations of the two elite family lineages in pre-modern Korea. We argue that the confluence of an ambiguous stratification system with a limited number of high-ranking offices generated a trade-off for parents between the quantity and quality of positions attained by their offspring. The result of the trade-off was unequal distributions of mobility-related family resources in order to maximize the lineage's collective goal, rather than to maximize individual children’s social ranks. Using a novel empirical strategy to take into account the heterogeneous resource-allocation within elite families, we present empirical evidence on associations between parents’ and grandparents’ social ranks and quality of offices achieved by children’s of elite Korean families.

Learn More (Paper) Learn More (Web appendix)