Stock News Sentiment Changes as a China Equity Factor

Summary

This study examines whether company news sentiment can help select Chinese stocks. It describes a news score where higher values generally indicate more positive coverage, then measures changes in the average score over a rolling lookback period. The reported dataset contains millions of screened news items, with coverage across many stocks and more news around reporting seasons, especially April.

The study reports favorable long-short results for the sentiment-change factor, particularly among China Securities 500 constituents. It compares weekly, biweekly, and monthly rebalancing, with biweekly results described as strongest overall. The factor has some positive correlation with recent returns and weaker relationships with other common factors; performance is reported to persist after removing exposure to ten such factors. These findings are historical and depend on the sample, universe, and implementation assumptions. The document provides summary statistics rather than enough detail to independently assess transaction costs, survivorship bias, data timing, or out-of-sample robustness.

Key ideas

• The factor tracks changes in average news sentiment over a chosen lookback period.
• News coverage is reported to rise during corporate reporting seasons.
• The sentiment-change signal is reported to perform particularly well in the China Securities 500 universe.
• Biweekly rebalancing is reported to outperform weekly and monthly schedules in the tested comparison.
• The reported signal retains performance after adjustment for common factors, though implementation risks remain unclear.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.