Analyzing Sentiment in Quarterly Earnings Calls — Q4 2023

We also analyzed Net Positivity scores in the various sections of the earnings call transcripts. For the S&P 500 this quarter, the Presenter Speech section had a Net Positivity score of 1.27%, while the Answer section had a score of 1.07%, showing the Executives of these companies used less favorable language during Q&A compared to their prepared remarks. The sector with the least amount of variance between the two transcript sections was Energy, which received a Net Positivity score of 1.31% during the Presenter Speech and 1.16% during the Answer section. The sector with the largest variance between sections was Industrials, where the Presenter Speech was 1.39% and the Answer Section was 1.13%.

Numeric Transparency

Overall, in Q4 2023, the S&P 500 had a Numeric Transparency score of 2.25%, a slight improvement from the Q3 2023 score of 2.17%, but lower than the last 12-month average of 2.30%. Utilities was once again the most transparent sector in the quarter with a score of 2.82% which was also an improvement versus the previous quarter. This was driven by favorable scores from Atmos Energy Corporation (NYSE:ATO) with 4.50%, NiSource Inc. (NYSE:NI) with 3.63% and Public Service Group Incorporated (NYSE:PEG). After Utilities, Information Technology was next best with a score of 2.40%, and Industrials with 2.36%. The least transparent sector this quarter was Communication Services with 1.82%. Some of the lower scores contributing to Communication Services were Netflix, Inc. (NasdaqGS:NFLX) with 1.05%, AT&T Inc. (NYSE:T) with 1.07% and Live Nation Entertainment (NYSE:LYV) with 1.18%. After Communication Services, Consumer Staples was the next lowest sector for Numeric Transparency with 1.89%, followed by Materials with 1.96%.

Language Complexity

In Q4 2023, the S&P 500 constituents had a Language Complexity score of 12.38, slightly up from Q3’s score of 12.36, showing the language in this quarter’s earnings call transcripts was slightly more complex and seen as less favorable. The individual S&P 500 sector with the least complex language this quarter was Industrials with 11.92. Some of the firms contributing to the more favorable sector score for Industrials were Parker-Hannifin Corporation (NYSE:PH) with 9.64, Textron (NYSE:TXT) with 10.30 and PACCAR Inc. (NasdaqGS:PCAR) also with 10.30. After Industrials was Materials with 12.13 and Information Technology with 12.16. The S&P 500 sector with the highest score (least favourable) for Language Complexity was Utilities with 13.05, contributed by more complex language in transcripts from firms such as Exelon (NasdaqGS:EXC) with 15.30, Dominion Energy, Inc. (NYSE:D) with 15.28, and NiSource Inc. (NYSE:NI) with 14.27. After Utilities, the sectors with the most complex language use were Communication Services with 12.79 and Health Care with 12.58.

Analyst Selectivity Ratio

For this quarter S&P 500 constituents had an Analyst Selectivity Ratio of 43.73%, slightly higher versus last quarter but below the average over the last year. Overall, the sectors with the highest Analyst Selectivity Ratio were Real Estate with a score of 51.50%, followed by Materials with 50.15%, and Industrials with 48.02%. The sectors with the lowest ratios were Communication Services with 25.05%, Utilities with 36.64%, and Consumer Discretionary with 37.79%. Analyzing the variance between Analyst Selectivity Ratio quarter-over-quarter, Communication Services had the largest decrease going from 29.79% in Q3 to 25.05% in Q4. The sector with the biggest increase between quarters was Utilities which increased from 31.31% in Q3 to 36.64% in Q4.

If you would like to receive the next infographic, register your interest here.

About Transcript Sentiment Scores

Transcript Sentiment Scores use natural language processing to provide a way to look at earnings call transcripts in a quantitative fashion. S&P Capital IQ Pro provides net positivity, numeric transparency, language complexity, and analyst selectivity ratio metrics for transcripts at the total, speaker, and component level. S&P Capital IQ Pro provides Net Positivity, Numeric Transparency, Language Complexity, and Analyst Selectivity Ratio metrics for transcripts at the: 1) Total level, 2) Speaker level, such as Executive or Analyst, and 3) Component level, such as Presentation Operator message, Presenter speech, Question, or Answer. Scores for companies are based on the most recent transcript of an earnings call in the calendar quarter that the event occurs. Scores are typically available 3 hours after a transcript is published to CIQ Pro. Scores are most effective when used to determine trends in sentiment by comparing current scores for a company vs. the prior quarters’ scores of the same company.

• Net Positivity: The net positivity score is based on the ratio of positive to negative words from the Loughran & McDonald’s (LM) Sentiment Word Lists and compares that to the total number of words.
• Numeric Transparency: The numeric transparency score is the ratio of numbers to words. A higher value means more use of numbers relative to words, which signifies a higher level of transparency. This is considered more objective and precise and thus, more favorable.
• Language Complexity: We use the Gunning Fog Index as a proxy for language complexity. Each score can be interpreted as the number of years of formal education a person needs to understand the text on the first reading. A lower score denotes simpler language and is viewed favorably.
• Analyst Selectivity Ratio: An analyst selectivity ratio is the percent of active analysts covering the stock that are allowed to ask questions during the call. A higher value is viewed favorably, and scores will range from 0% to 100%.

^{Source: S&P Capital IQ Pro. Data as of December 5, 2023.}

^References:

^{Zhao, F. "Natural Language Processing – Part II: Stock Selection" (September 2018). Natural Language Processing – Part II: Stock Selection | S&P Global Market Intelligence (spglobal.com)}

^{Zhao, F."Natural Language Processing – Part III: Feature Engineering" (January 2020). Natural Language Processing – Part III: Feature Engineering | S&P Global Market Intelligence (spglobal.com)}