Inthis article, we present a machine learning-based solution for matching the performance of the gold standard of double-blind human coding when it comes to content analysis in comparative politics. We combine a quantitative text analysis approach with supervised learning and limited human resources in order to classify the front-page articles of a leading Hungarian daily newspaper based on their full text. Our goal was to assign items in our dataset to one of 21 policy topics based on the codebook of the Comparative Agendas Project. The classification of the imbalanced classes of topics was handled by a hybrid binary snowball workflow. This relies on limited human resources as well as supervised learning; it simplifies the multiclass problem to one of binary choice; and it is based on a snowball approach as we augment the training set with machine-classified observations after each successful round and also between corpora. Our results show that our approach provided better precision results (of over 80% for most topic codes) than what is customary for human coders and most computer-assisted coding projects. Nevertheless, this high precision came at the expense of a relatively low, below 60%, share of labeled articles.
The article investigates the dynamics of budgeting and its explanatory factors in Hungary based on a new database. Previous work for the period between 1991 and 2013 demonstrated that year-on-year changes in budgetary allocations by policy topics show a leptokurtic distribution. This distribution of policy changes is generally associated with the notion of punctuated equilibrium. We extend this analysis to cover over 155 years of Hungarian budgetary history. Our investigation of a database of 2580 spending category observations (covering the period between 1868 and 2013) lends support for the theory of punctuated equilibrium. We also analysed the impact of political regimes on budgetary dynamics. Here we provided empirical evidence for the validity of the informational advantage hypothesis which states that democracies will show lower level of kurtosis than other political regimes. This finding is also in line with the results of available comparative studies.
The paper applies two core theoretical frameworks of budgetary change-incrementalism and punctuated equilibrium theory-to a new database of Hungarian final accounts data for the period 1991 through 2013. Based on our analysis trends in Hungarian budgeting are in line with available comparative evidence suggesting that yearly changes of budget outlays in policy domains are best characterized by a punctuated equilibrium model. The most significant variable in predicting whether an observation would fall into the equilibrium or punctuated group was the share of the given policy domain of total outlays. However, alternative explanatory variables, such as the electoral cycle, the fiscal cycle and the business cycle had no effect on the results.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.