News-sentiment networks as a risk indicator

TL;DR

This paper introduces a sentiment-based network risk algorithm that predicts stock price declines up to 70 days after measuring news sentiment and company co-occurrences, revealing significant predictive power.

Contribution

It presents a novel algorithm combining news sentiment and co-occurrence data to measure network risk and predict stock declines over a month in advance.

Findings

Highest risk correlates with increased stock decline probability.

Maximum predictive accuracy occurs around 28 days after risk measurement.

The model achieves up to 13 percentage points in probability difference.

Abstract

To understand the relationship between news sentiment and company stock price movements, and to better understand connectivity among companies, we define an algorithm for measuring sentiment-based network risk. The algorithm ranks companies in networks of co-occurrences, and measures sentiment-based risk, by calculating both individual risks and aggregated network risks. We extract relative sentiment for companies to get a measure of individual company risk, and input it into our risk model together with co-occurrences of companies extracted from news on a quarterly basis. We can show that the highest quarterly risk value outputted by our risk model, is correlated to a higher chance of stock price decline, up to 70 days after a risk measurement. Our results show that the highest difference in the probability of stock price decline, compared to the benchmark containing all risk values for the same period, is during the interval from 21 to 30 days after a quarterly measurement. The highest average probability of company stock price decline, is found at a delay of 28 days, after a company has reached its maximum risk value. The highest probability differences for a daily decline were calculated to be 13 percentage points.