Search
Browse By Day
Browse By Time
Browse By Person
Browse By Mini-Conference
Browse By Division
Browse By Session or Event Type
Browse Sessions by Fields of Interest
Browse Papers by Fields of Interest
Search Tips
Conference
Location
About APSA
Personal Schedule
Change Preferences / Time Zone
Sign In
X (Twitter)
Ideology plays a central role in shaping the forms and directions of human societies, yet accurate measurement of individual preferences over various issue domains remains a challenge, especially in countries where survey-based measures are hard to obtain. In this article, we develop a new measurement strategy based on the public’s cultural consumption patterns and demonstrate its applicability in China using an original dataset of over a billion online book, movie, and music reviews from 170 million users collected from one of China’s most popular social media platforms. We develop a three-step algorithm: First, we identify a subset of “seed books” with strong ideological connotations; we then scale the large user rating-product network to obtain the low-dimensional numeric representations (i.e., embeddings) of users who consume these books; finally, we calculate the distances among these embeddings to map a large set of users, producers, and cultural products onto the same ideological space. Our preliminary findings suggest that there exist several distinct clusters of political, economic, and social preferences among educated Chinese citizens that do not follow a simple unidimensional distribution as is common in the West. In particular, free-market ideologies seem to be compatible with preferences for both centralized and democratic political systems. Moreover, we show that there are significant temporal variations in the ideology of content of published books during the reform era (1976–present), with the year 2008 marking the high point of Chinese liberalism, followed by a significant and accelerated left turn afterward.