blog Market Intelligence /marketintelligence/en/news-insights/blog/analyzing-sentiment-in-quarterly-earnings-calls-q4-2022 content esgSubNav
In This List

Analyzing Sentiment in Quarterly Earnings Calls - Q4 2022


European banking sector outlook 2023

Volume of Investment Research Reports on Generative AI Skyrocketed in Q1 2023


Insight Weekly: Bank oversight steps up; auto insurers’ dismal year; VC investment slumps


Street Talk | Episode 110: Bears use banks as ‘weapons of destruction' to force change in Fed policy

Analyzing Sentiment in Quarterly Earnings Calls - Q4 2022

In the below, we used Transcript Sentiment Scores to analyze the performance of the S&P 500 and its constituents. 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.

*Q4 refers to the date the earnings call transcript was released not the earnings period it represents.

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.

In Q4* 2022, the S&P 500 had a net positivity score of 0.96%, down just slightly from it’s Q3 number of 1.00%. Over the last few quarters, we’ve seen this score continue to drop from it’s Q1 number of 1.18%, and its currently trending below it’s previous four quarter average of 1.08%. Overall net positivity could continue to drop going into 2023, but the U.S. November Inflation number (7.1%) might be a good sign that market conditions will improve next year. Looking at the individual sectors of the S&P 500, Communication Services posted the highest net positivity score at 1.30%, followed very closely by Consumer Discretionary at 1.29%. Both sectors improved quite a bit from their 1.21% score in Q3 but are still trending lower than their previous four quarter average of 1.34%. The lowest sector scores were Financials at 0.50% and Real Estate at 0.64%. Both sectors are well below their Q3 scores, as well as their previous four quarter average. Real Estate specifically saw the biggest decrease in net positivity in Q4, going from 0.93% in Q3 to 0.64% in Q4. Some factors contributing to this decrease are CBRE Group (NYSE:CBRE) and Vornado Realty Trust (NYSE:VNO), which received -0.54% and -0.22%, respectively. Both of which had large net positivity decreases and led to the overall decline in the Real Estate sector quarter over quarter.

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.

Overall, in Q4 2022, the S&P 500 had a numeric transparency score of 2.25%, improving from it’s Q3 score of 2.13%. Although it’s slightly below the previous four quarter average of 2.27%, this score has rebounded quite a bit from 2.12% in Q2. A higher score means more transparency so it’s nice to see this number trending in the right direction going into 2023. Looking at the individual sectors, Utilities received the highest score for numeric transparency with 2.81%, well above it’s Q3 score of 2.35%, and above their previous four quarter average of 2.68%. Industrials was the next highest sector with a score of 2.44%, but several other sectors Information Technology (2.42%), Real Estate (2.42%), and Health Care (2.35%) were not far off. The lowest score went to Consumer Staples at 1.86%, which also had the lowest previous four quarter average at 1.86%.

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.

In Q4 2022, the S&P 500 had a language complexity score of 12.36, up slightly from the Q3 and Q2 scores of 12.30 and 12.29, respectively. This was also just a bit above the previous four quarter average of 12.35.  The sector with the lowest score (more favorable) was Industrials with 11.90, which also had the lowest score in Q3 with 11.89. The next lowest sector score after Industrials was Materials with 11.98, which was down slightly compared to its Q3 score of 12.03. The sector with the most complex language (less favorable) used in earnings call transcripts was Utilities at 12.97. Interesting given they were the highest in numeric transparency as well. After Utilities, the next highest sector was Health Care at 12.69, which makes sense given the information discussed in these earnings calls.

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%.

Overall, for Q4 2022, the S&P 500 had an analyst selectivity ratio of 42.43%, down from Q3 (42.73%), and down from the previous four quarter average of 42.59%. For the individual sectors, Industrials had the highest percentage of active analysts allowed to ask questions during earnings calls with 50.60%, although this number was down compared to the Q3 number of 52.44%, and their Q2 number of 52.01%. After Industrials, Materials was the next highest at 50.36%. The sector with the lowest analyst selectivity ratio was Communication Services at 26.72%. This score was the lowest number for any sector over the last year, and Communication Services previous four quarter average of 30.50%. Outside of Communication Services, Energy was the next lowest sector with 32.37%.


Zhao, F.  “Natural Language Processing – Part II: Stock Selection” (September 2018). Natural Language Processing – Part II: Stock Selection | S&P Global Market Intelligence (

Zhao, F.  “Natural Language Processing – Part III: Feature Engineering” (January 2020). Natural Language Processing – Part III: Feature Engineering | S&P Global Market Intelligence (

Learn more about Market Intelligence
Request Follow Up

Analyzing Sentiment in Quarterly Earnings Calls Q3 2022

Read Now