We introduce a general approach for analyzing large-scale text-based data, combining the strengths of neural network language processing and generative statistical modeling to create a factor structure of unstructured data for downstream regressions typically used in social sciences. We generate...

The majority of state-owned enterprises (SOEs) in China were privatized through ownership reforms over the last two decades. Using a comprehensive dataset of all medium and large enterprises in China between 1998 and 2013, we show that privatized SOEs continue to benefit from government support...