Are Bots Listening in on Your Earnings Calls?

Your investors can use natural language processing and sentiment analysis to detect hidden sentiment on earnings calls. Here’s what you need to know.

Expert View

Whether you’re a CEO, CFO or a head of investor relations, you’re used to planning for quarterly earnings calls. But there’s one thing you might not be prepared for — choosing your words carefully, because bots will be listening…and they are on the lookout for hidden details about corporate performance.

Is your CEO or CFO sending the right message — to the bots who might be listening?

More than 13,000 public companies produce over 30,000 hours of earnings calls per year, and about 60% of each call is spent on the Q&A session. CEOs and CFOs are most often on the hot seat as portfolio managers and investment analysts look for clues to a company’s future. Is your CEO or CFO sending the right message to the bots who might be listening?

Yes, bots. As investors look for an edge, they are turning to automated speech and text analysis for additional clues about performance. The use of nonfinancial data such as this — referred to in investment analytics as “nontraditional data” — is a growing part of investor information services (e.g., Bloomberg) as firms look for new ways to establish what the return on investment might be from rapidly evolving machine learning approaches.

Learn more: Lie Detection and Sentiment Analysis on Earnings Calls

What bots look for

Natural language processing (NLP) is the use of software to analyze human language using complex algorithms. Sentiment analysis measures the positivity or negativity of a set of prose to understand hidden emotions behind the words. The general idea, then, is that NLP and sentiment analysis can identify underlying and unspoken meaning about company performance and potential that isn’t explicit in direct language from senior leaders.

Key indicators of hidden sentiment include indirect answers to questions, exuberant words, a lack of fillers and qualifying statements.

By staying informed of new trends and developments in NLP and sentiment analysis, CEOs, CFOs and investor relations leaders can avoid major misinterpretations arising from simple word choice and syntax.

Read more: Digital Demands CFOs Rethink How to Deliver Value

Word choices and syntax to avoid

Software and analysis experts have identified a series of markers that are more likely to indicate deception or hidden sentiment.

David Larcker, professor of accounting at Stanford University’s Graduate School of Business, pioneered research in this area and found three common signs that company representatives aren’t telling the truth:

  1. Failure to directly answer an analyst’s question
  2. Using words like “my team” and “we” more than “I” or “myself”
  3. Using exuberant words like “amazing” or “awesome”

Other words that analysis firms look out for include “but” and “if,” as well as other contrasting or qualifying prepositions. In addition, experts advise against qualifying phrases such as “as I said before” or “to the best of my knowledge.”

Lastly, contrary to common belief, research shows dishonest executives are less likely to stammer or use filler phrases such as “um,” “uh” or “err.” This is likely due to heavy coaching and predeveloped talking points for uneasy topics.

Quarterly earnings calls are one of the most powerful tools a company uses to communicate with the investment community. As your investor relations team prepares for the next call, make sure they don’t ignore these emerging technologies.

Top Insights for the C-Suite
Mobilize Every Function in the Organization for Digitalization
Download the free e-Book
Tim_Raiswell

Tim Raiswell VP, Research and Agenda Manager for the Gartner financial strategy key initiative, is a business advisor and researcher for CFOs and heads of FP&A.

 

Gartner for Finance Leaders clients can read more about lie detection on earnings calls, how companies structure earnings calls and ways to improve the earnings call process.