A5015448535- Defense, Military, and Policy Studies
- Media Influence and Politics
- Hate Speech and Cyberbullying Detection
- Misinformation and Its Impacts
- Sentiment Analysis and Opinion Mining
- Fiscal Policy and Economic Growth
- Computational and Text Analysis Methods
United States Army
2023-2024
Carnegie Mellon University
2023-2024
Theoretical and empirical research on causes consequences of defense spending is plentiful. Most this uses ‘top line’ data, either as a share GDP or raw monetary figure. Empirical has been limited, however, by the ‘blunt’ nature which does not help to explain what countries are on. We introduce dataset that provides information disaggregated from 35 NATO EU members over many 51 years. discuss main features data in paper, replication files will enable other scholars automate accessing it...
Media bias has been extensively studied by both social and computational sciences. However, current work still a large reliance on human input subjective assessment to label biases. This is especially true for cable news, which continued presence in American media but lack of text-based identification research. To address these issues, we develop an unsupervised machine learning method characterize the news programs without any input. relies analysis what topics are mentioned through Named...
Theoretical and empirical research on causes consequences of defense spending is plentiful. Most this uses “top line” data, either as a share GDP or raw monetary figure. Empirical has been limited, however, by the “blunt” nature which does not help explain what countries are on. We introduce dataset that provides information disaggregated from 35 NATO EU members over many 51 years. discuss main features data in paper, replication files will enable other scholars to automate accessing it...
Media bias has been extensively studied by both social and computational sciences. However, current work still a large reliance on human input subjective assessment to label biases. This is especially true for cable news research. To address these issues, we develop an unsupervised machine learning method characterize the of programs without any input. relies analysis what topics are mentioned through Named Entity Recognition how those discussed Stance Analysis in order cluster with similar...