ABSTRACT

We examine the practice of web-crawling architecture through two logics: combinational logic (CL) and sequential logic (SL) and adopt a test ground on the relationship between price informativeness and corporate social responsibility (CSR) news releases among publicly listed former unicorns. Our results show that the CL approach is more optimal than the SL approach regarding time consumption, storage efficiency and data accuracy, which suggest that CSR media exposures have substantial influence on price informativeness. Both positive (optimistic) and negative (pessimistic)-toned CSR information increases price informativeness. We find that the Diction wordlist displays higher classification accuracy when analyzing CSR news release.

摘要

我们通过组合逻辑 (CL) 和顺序逻辑 (SL) 两种逻辑来检验网络爬虫架构的实践，并在公开上市的前独角兽中对价格信息量与企业社会责任 (CSR) 新闻发布之间的关系进行测试。我们的结果表明，在时间消耗、存储效率和数据准确性方面，CL 方法比 SL 方法更优化，这表明 CSR 媒体曝光对价格信息量有很大影响。积极（乐观）和消极（悲观）的 CSR 信息都增加了价格信息量。我们发现在分析 CSR 新闻发布时，Diction 词表显示出更高的分类准确度。