Clear Messages, Ambiguous Audiences: Measuring Interpretability in Political Communication

Text-based measurement in political research often treats classi6ication disagreement as random noise. We examine this assumption using con6idence-weighted human annotations of 5,000 social media messages by U.S. politicians. We 6ind that political communication is generally highly legible, with mean con6idence exceeding 0.99 across message type, partisan bias, and audience classi6ications. However, systematic variation concentrates in the constituency category, which exhibits a 1.79 percentage point penalty in audience classi6ication con6idence. Given the high baseline of agreement, this penalty represents a sharp relative increase in interpretive uncertainty. Within messages, intent remains clear while audience targeting becomes ambiguous. These patterns persist with politician 6ixed effects, suggesting that measurement error in political text is structured by strategic incentives rather than idiosyncratic coder error.

• Publication year

  2026

• Venue

  Unknown venue

• Publication date

  2026-01-28

• Fields of study

  Economics, Political Science

• Identifiers
  arXiv 2601.20912
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Text as Data: A New Framework for Machine Learning and the Social Sciences

  2023cited by this paper
• Communication in the Age of Twitter: The Nature of Online Deliberation

  2020cited by this paper
• Who Leads? Who Follows? Measuring Issue Attention and Agenda Setting by Legislators and the Mass Public Using Social Media Data

  2019cited by this paper
• Social Media and Fake News in the 2016 Election

  2017cited by this paper
• Crowd-sourced Text Analysis: Reproducible and Agile Production of Political Data

  2016cited by this paper
• Representational Style in Congress: What Legislators Say and Why It Matters

  2013cited by this paper
• A 61-million-person experiment in social influence and political mobilization

  2012cited by this paper
• The Effect of Newspaper Entry and Exit on Electoral Politics

  2011cited by this paper
• A Method of Automated Nonparametric Content Analysis for Social Science

  2010cited by this paper
• Data Quality from Crowdsourcing: A Study of Annotation Selection Criteria

  2009cited by this paper
• Strategic Communication with Lying Costs

  2009cited by this paper
• A Scaling Model for Estimating Time-Series Party Positions from Texts

  2007cited by this paper
• Handcuffs for the Grabbing Hand? Media Capture and Government Accountability

  2006cited by this paper
• Political Motivations ∗

  2005cited by this paper
• Reliability in Content Analysis: Some Common Misconceptions and Recommendations

  2004cited by this paper
• Out of Step, Out of Office: Electoral Accountability and House Members' Voting

  2002cited by this paper
• Measurement error in survey data

  2001cited by this paper
• Mismeasured Variables in Econometric Analysis: Problems from the Right and Problems from the Left

  2001cited by this paper
• The Effects of Negative Political Advertisements: A Meta-Analytic Assessment

  1999cited by this paper
• The Theory of Political Ambiguity

  1976cited by this paper
• Congress: The Electoral Connection

  1975cited by this paper
• The Strategy of Ambiguity: Uncertainty and Electoral Competition

  1972cited by this paper

• No citing papers are available for this paper.