A Framework for Measuring How News Topics Drive Stock Movement
Qizhao Chen
TL;DR
The paper addresses the limitation of aggregate sentiment in financial news analysis by proposing topic-level measurement of news impact on stock returns. It encodes headlines into semantic embeddings using a pretrained sentence transformer, clusters them with K-means into distinct topics, and links daily topic exposures to next-day returns via ordinary least squares regression, $R_t = \alpha + \sum_{k=0}^{K-1} \beta_k D_{t,k} + \epsilon_t$. A normalized topic-importance score, $I_k = \frac{|\hat{\beta}_k|}{\sum_{j=1}^{K} |\hat{\beta}_j|}$, ranks topics by their explanatory power. Applied to Apple Inc. (AAPL), the framework finds some topics significantly associated with positive or negative next-day returns (e.g., Topic_0 negative, Topic_4 positive) while others show no measurable effect, illustrating the value of topic-level analysis for predictive finance.
Abstract
In modern financial markets, news plays a critical role in shaping investor sentiment and influencing stock price movements. However, most existing studies aggregate daily news sentiment into a single score, potentially overlooking important variations in topic content and relevance. This simplification may mask nuanced relationships between specific news themes and market responses. To address this gap, this paper proposes a novel framework to examine how different news topics influence stock price movements. The framework encodes individual news headlines into dense semantic embeddings using a pretrained sentence transformer, then applies K-means clustering to identify distinct news topics. Topic exposures are incorporated as explanatory variables in an ordinary least squares regression to quantify their impact on daily stock returns. Applied to Apple Inc., the framework reveals that certain topics are significantly associated with positive or negative next-day returns, while others have no measurable effect. These findings highlight the importance of topic-level analysis in understanding the relationship between news content and financial markets. The proposed framework provides a scalable approach for both researchers and practitioners to assess the informational value of different news topics and suggests a promising direction for improving predictive models of stock price movement.