A股上市公司股吧文本统计数据

中国上市公司在主要的行情网络平台进行每日行情发布，并建立起投资者之间互动、交流的平台。来自全国各地的投资者在上市公司的线上股票交流平台进行发帖、回帖等交流互动，形成了超大量级的中国股市投资相关的文本语料数据。研究者足以通过超大量级的投资者互动数据来观察投资者的市场判断、个人情绪等多维度信息。  近年来，国内外研究者们发现：

Chinese listed companies release daily market quotations on major online stock market platforms, and establish interactive communication platforms for investors. Investors from all over the country conduct interactive communications such as posting and replying to posts on the online stock communication platforms of listed companies, forming a massive text corpus of data related to China's stock market investment. Researchers can sufficiently observe multi-dimensional information such as investors' market judgments and personal sentiments through this massive corpus of investor interaction data. In recent years, researchers both domestically and internationally have found that:

搜集汇总

背景与挑战

背景概述

该数据集统计了A股上市公司股吧的发帖和回帖文本数据，时间跨度为2008年至2024年，包含超过三亿条发帖和四亿条回帖。数据集不仅统计了各时间段发帖回帖数量，还基于情感分析提供了正面、负面和中性帖子的占比及数量，为研究投资者情绪与市场行为提供了高质量数据支持。