Journal of Network Theory in Finance

News-sentiment networks as a company risk indicator

Thomas Forss and Peter Sarlin

  • We extract networks of companies from text-based news and compare how sentiment in news affect the stock prices of the companies
  • We find that aggregating news-sentiment on a quarterly basis can signal when a company stock price is at higher probability of falling
  • We calculate news-sentiment risk for companies and show that a company reaching the maximum risk value is up to 13 percentage points more likely to have reduced stock price

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. We then input this into our risk model together with co-occurrences of companies extracted from news on a quarterly basis. We show that the highest quarterly risk value outputted by our risk model is correlated to a higher chance of stock price decline up to seventy days after a quarterly risk measurement. Our results show that the highest difference in the probability of stock price decline is found during the interval from twenty-one to thirty days after a quarterly measurement. The highest average probability of company stock price decline is seen twenty-eight days after a company has reached the maximum risk value using our model, with a 13 percentage points increased chance of stock price decline.

Sorry, our subscription options are not loading right now

Please try again later. Get in touch with our customer services team if this issue persists.

New to View our subscription options

You need to sign in to use this feature. If you don’t have a account, please register for a trial.

Sign in
You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Sign in.

Alternatively you can request an individual account here