按年被提到
20232023 · 2 次2026
AI 安全、伦理与社会影响›大模型与人类行为·arXiv:2303.16779 · cs.CL

Language Models Trained on Media Diets Can Predict Public Opinion

Eric Chu, Jacob Andreas, Stephen Ansolabehere, Deb Roy · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 3 人首次 2023-04-02 · 最近 2025-06-02
3不同的人
2活跃月份
3讨论串
35被引(OpenAlex)
arXiv 摘要(候选层不写导读)

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.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)
讨论串评论janalsncm · 2023-04

“This is pretty scary if true. Imagine you would like to influence an individual’s opinion in a very specific way. At present the only way to do this is to write articles in the general vicinity of your cause. However, with an accurate forecast of public opinion, it’s possible to tune the input content such that the output is most closely aligned with the …”

Language models trained on media diets can predict public opinion原评论 ↗
被提交为 story · 3 次