Analysis and sentiment detection in online reviews of tax professionals: A comparison of three software packages

Candace L. Witherspoon, Dan N. Stone

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

This study analyzes the "tax talk" in online client reviews of tax preparers, and evaluates off-the-shelf (SentiStrength, LIWC2007, and DICTION 6.0) and customized software packages' detection of sentiment in these reviews. Compared to human-coded sentiment, three off-the-shelf programs poorly assess client sentiment. We adapted two software packages, SentiStrength and LIWC2007, to "tax talk" by splitting the sample into learning and holdout segments (n = 50 each). Results for SentiStrength with a customized dictionary and keywords evidenced high validity. The results suggest that client reviews of tax preparers contain unique taxation language.

Original languageEnglish
Pages (from-to)89-115
Number of pages27
JournalJournal of Emerging Technologies in Accounting
Volume10
Issue number1
DOIs
StatePublished - Dec 2013

Keywords

  • Content analysis
  • Professional tax services
  • Sentiment analysis
  • Social analytics

ASJC Scopus subject areas

  • Accounting
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Analysis and sentiment detection in online reviews of tax professionals: A comparison of three software packages'. Together they form a unique fingerprint.

Cite this