Large-scale Quantitative Evidence of Media Impact on Public Opinion toward China

Abstract

Do mass media influence people's opinion of other countries? Using BERT, a deep neural network-based natural language processing model, we analyze a large corpus of 267,907 China-related articles published by The New York Times since 1970. We then compare our output from The New York Times to a longitudinal data set constructed from 101 cross-sectional surveys of the American public's views on China. We find that the reporting of The New York Times on China in one year explains 54% of the variance in American public opinion on China in the next. Our result confirms hypothesized links between media and public opinion and helps shed light on how mass media can influence public opinion of foreign countries.

Figures (4)

• Figure 1: Public opinion of Americans toward China. This time series is aggregated from 101 cross-sectional surveys from 1974 to 2019 that asked relevant questions about attitudes toward China, ranging from -100% to 100% with the year of 1974 as baseline. Years with attitudes above zero show a more favorable attitude than that in 1974, with a peak of 73% in 1987. Years with attitudes below zero show a less favorable attitude than that in 1974, with a lowest level of -24% in 1976. The time series is shown with 95% confidence interval.
• Figure 2: Topic-specific yearly volume of The New York Times articles with sentiment on China from 1970 to 2019. In each year we report in each topic the number of positive and negative articles, while ignoring neutral/irrelevant articles. The media have consistently high attention on reporting China government & administration, democracy, globalization, and culture. There are emerging interests on China's economics, marketization, and welfare & well-being since 1990s. Note that the sum of the stacks does not equal to the total volume of articles about China, because each article may express sentiment in none or multiple topics.
• Figure 3: Sentiments on The New York Times on China in eight topics from 1970 to 2019. Each panel reports the trend of yearly media attitude toward China in each of eight domains since 1970. The media attitude is measured as the percentages of positive articles and negative articles respectively. US-China relation milestones are marked as gray dots. New York Times express diverging but consistent attitudes in the eight domains, with negative articles consistently common in ideology, government, democracy, and welfare, and positive sentiments common in economic, globalization and culture. Standard errors are too small to be visible (below 1.55% in all topics all years).
• Figure 4: Regressing public opinion of Americans toward China on The New York Times sentiments. The public opinion (solid), as a time series, is well fitted by the media sentiments on two selected topics, namely Culture and Democracy, in the previous year. The dash line shows a linear prediction based on the fractions of positive articles on Culture and negative articles on Democracy in the previous year. The public opinion is shown with 95% confidence interval, and the fitted line is shown with one standard error.