Public opinion reflects and shapes societal behavior, but the traditional survey-based tools to measure it are limited. We introduce a novel approach to probe media diet models -- language models adapted to online news, TV broadcast, or radio show content -- that can emulate the opinions of subpopulations that have consumed a set of media. To validate this method, we use as ground truth the opinions expressed in U.S. nationally representative surveys on COVID-19 and consumer confidence. Our studies indicate that this approach is (1) predictive of human judgements found in survey response distributions and robust to phrasing and channels of media exposure, (2) more accurate at modeling people who follow media more closely, and (3) aligned with literature on which types of opinions are affected by media consumption. Probing language models provides a powerful new method for investigating media effects, has practical applications in supplementing polls and forecasting public opinion, and suggests a need for further study of the surprising fidelity with which neural language models can predict human responses.

翻译：摘要：公众舆论既反映又塑造社会行为，但传统基于调查的测量工具存在局限性。我们提出一种探测媒体信息流模型的新方法——即适应于网络新闻、电视广播或电台节目内容的语言模型——这类模型能够模拟接受特定媒体信息群体的观点。为验证该方法，我们以美国全国代表性调查中关于新冠疫情与消费者信心的舆论数据为基准。研究表明该方法：（1）能预测调查回复分布中的人类判断，且对措辞与媒体曝光渠道具有鲁棒性；（2）对密切追随媒体的群体建模更准确；（3）与现有文献中关于媒体消费影响何种观点的结论一致。探测语言模型为研究媒体效应提供了强有力的新手段，在补充民意调查与预测公众舆论方面具有实际应用价值，并提示需进一步研究神经语言模型预测人类反应时展现出的惊人准确性。