Automatic summarization of earnings releases: Attributes and effects on investors’ judgments

Research output: Contribution to journalArticleScientificpeer-review

Abstract

Firms often include summaries with earnings releases. However, manager-generated summaries may be prone to strategic tone and content management, compared to the underlying disclosures they summarize. In contrast, computer algorithms can summarize text without human intervention and may provide useful summary information with less bias. We use multiple methods to provide evidence regarding the characteristics of algorithm-based summaries of earnings releases compared to those provided by managers. Results suggest that automatic summaries are generally less positively biased, often without sacrificing relevant information. We then conduct an experiment to test whether these differing attributes of automatic and management summaries affect individual investors’ judgments. We find that investors who receive an earnings release accompanied by an automatic summary arrive at more conservative (i.e., lower) valuation judgments and are more confident in those judgments. Overall, our results suggest that summaries affect investors’ judgments and that these effects differ for management and automatic summaries.
Original languageEnglish
JournalReview of Accounting Studies
DOIs
Publication statusE-pub ahead of print - Feb 2019

Fingerprint

Investors
Summarization
Managers
Disclosure
Content management
Multiple use
Experiment
Individual investors
Strategic management

Keywords

  • Management summary
  • Automatic summary
  • Investor Judgment
  • Earnings Release
  • Individual Investors

Cite this

@article{721f64f4033e453ba3e72bbc535d7575,
title = "Automatic summarization of earnings releases: Attributes and effects on investors’ judgments",
abstract = "Firms often include summaries with earnings releases. However, manager-generated summaries may be prone to strategic tone and content management, compared to the underlying disclosures they summarize. In contrast, computer algorithms can summarize text without human intervention and may provide useful summary information with less bias. We use multiple methods to provide evidence regarding the characteristics of algorithm-based summaries of earnings releases compared to those provided by managers. Results suggest that automatic summaries are generally less positively biased, often without sacrificing relevant information. We then conduct an experiment to test whether these differing attributes of automatic and management summaries affect individual investors’ judgments. We find that investors who receive an earnings release accompanied by an automatic summary arrive at more conservative (i.e., lower) valuation judgments and are more confident in those judgments. Overall, our results suggest that summaries affect investors’ judgments and that these effects differ for management and automatic summaries.",
keywords = "Management summary, Automatic summary, Investor Judgment, Earnings Release, Individual Investors",
author = "Eddy Cardinaels and Stephan Hollander and Brian White",
year = "2019",
month = "2",
doi = "10.1007/s11142-019-9488-0",
language = "English",
journal = "Review of Accounting Studies",
issn = "1380-6653",
publisher = "Springer New York",

}

Automatic summarization of earnings releases : Attributes and effects on investors’ judgments. / Cardinaels, Eddy; Hollander, Stephan; White, Brian.

In: Review of Accounting Studies, 02.2019.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Automatic summarization of earnings releases

T2 - Attributes and effects on investors’ judgments

AU - Cardinaels, Eddy

AU - Hollander, Stephan

AU - White, Brian

PY - 2019/2

Y1 - 2019/2

N2 - Firms often include summaries with earnings releases. However, manager-generated summaries may be prone to strategic tone and content management, compared to the underlying disclosures they summarize. In contrast, computer algorithms can summarize text without human intervention and may provide useful summary information with less bias. We use multiple methods to provide evidence regarding the characteristics of algorithm-based summaries of earnings releases compared to those provided by managers. Results suggest that automatic summaries are generally less positively biased, often without sacrificing relevant information. We then conduct an experiment to test whether these differing attributes of automatic and management summaries affect individual investors’ judgments. We find that investors who receive an earnings release accompanied by an automatic summary arrive at more conservative (i.e., lower) valuation judgments and are more confident in those judgments. Overall, our results suggest that summaries affect investors’ judgments and that these effects differ for management and automatic summaries.

AB - Firms often include summaries with earnings releases. However, manager-generated summaries may be prone to strategic tone and content management, compared to the underlying disclosures they summarize. In contrast, computer algorithms can summarize text without human intervention and may provide useful summary information with less bias. We use multiple methods to provide evidence regarding the characteristics of algorithm-based summaries of earnings releases compared to those provided by managers. Results suggest that automatic summaries are generally less positively biased, often without sacrificing relevant information. We then conduct an experiment to test whether these differing attributes of automatic and management summaries affect individual investors’ judgments. We find that investors who receive an earnings release accompanied by an automatic summary arrive at more conservative (i.e., lower) valuation judgments and are more confident in those judgments. Overall, our results suggest that summaries affect investors’ judgments and that these effects differ for management and automatic summaries.

KW - Management summary

KW - Automatic summary

KW - Investor Judgment

KW - Earnings Release

KW - Individual Investors

U2 - 10.1007/s11142-019-9488-0

DO - 10.1007/s11142-019-9488-0

M3 - Article

JO - Review of Accounting Studies

JF - Review of Accounting Studies

SN - 1380-6653

ER -