Alternative data is one of the more interesting data-related trends of recent years, with a growing number of use cases highlighting the potential for unusual data sources to make a significant difference to how decisions are made.

The latest example comes via new research from ANU, which shows how Twitter data can provide highly accurate profit forecasts for consumer goods companies.

The researchers looked at around 250,000 tweets made about the 10 biggest airlines operating in North America, including those with both positive and negative sentiment.

Sharing sentiment

The data showed a clear correlation between the kind of tweets people were sharing and the overall financial health of the business.  For instance, if most tweets about an airline were negative, whether about flight delays, the food on board or the luggage service provided, the more accurate profit forecasts tended to be, especially when those forecasts were of a drop in profits.

It’s a finding that leads the researchers to believe that data from Twitter can be a much more powerful source of financial insight than is perhaps currently believed.

“We found negative tweets increased analyst forecast accuracy, and they generally pointed to analysts expecting a greater likelihood of less profit. The less negative tweets, the better the expected profit figure,” they say.  “These results show Twitter is a reasonably good indicator of profit levels, and the more tweets there are, the closer the forecasts are to being correct.”

The value of the data comes from the real-time nature of information collected.  This is especially so in a financial context as you’re getting practically live insight into how customers feel and are engaging with brands.

“Tweets come directly from the customers as immediate feedback,” the researchers say.  “Analysts rely on timely information, because they typically update their forecast each month. But other public sources of relevant information may not be available throughout the year.”