arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.16779cs.CLcs.LG
收藏

媒体饮食训练的语言模型可以预测舆论

Language Models Trained on Media Diets Can Predict Public Opinion

Massachusetts Institute of Technology(麻省理工学院);Google(谷歌);Harvard University(哈佛大学)

Eric Chu, Jacob Andreas, Stephen Ansolabehere, Deb Roy

摘要:

舆论反映和塑造社会行为,但传统的基于调查的工具来衡量它是有限的。我们引入了一种新的方法来探索媒体饮食模型-适应在线新闻,电视广播或广播节目内容的语言模型-可以模仿消费了一组媒体的亚群的意见。为了验证这种方法,我们使用美国全国代表性的COVID-19和消费者信心调查中表达的意见作为基础事实。我们的研究表明,这种方法是(1)预测调查响应分布中的人类判断,并对媒体曝光的措辞和渠道具有鲁棒性,(2)更准确地建模更密切关注媒体的人,以及(3)与哪些类型的观点受到媒体消费影响的文献保持一致。探测语言模型提供了一个强大的新方法来调查媒体的影响,在补充民意调查和预测公众舆论的实际应用,并建议需要进一步研究的惊人的保真度与神经语言模型可以预测人类的反应。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑