【Workshop for MLinEcon第110期】资本市场中的AI测谎仪

文章预览

【题目】 Measuring Misinformation in Financial Markets （ Working Paper, 2024 ） 【摘要】 We propose a framework for measuring firm-level misinformation. By leveraging advanced machine learning and AI technologies, we transform and categorize unstructured text into comparable information, extract "truth" from each set of comparable information, and quantify the degree of misinformation based on divergence from the "truth." Applying our framework to analyze 254.8 million textual materials, we validate its effectiveness in quantifying misinformation. We find that firms with weaker balance sheets and poorer governance structures exhibit higher misinformation, and misinformation spikes during major corporate events. We also demonstrate that misinformation significantly impacts investors' attention, trading volumes, stock returns, and risks. 【汇报人】王子路（复旦大学经济学院博士研究生） 【时间】 2024 年 9 月 10 日（周二） 20:30-22:00 ………………………………