Framing & Political Discourse #

What this framework does #

Analyzes how political texts construct persuasive realities by activating semantic frames, positioning actors, and tapping into moral systems. This prompt operationalizes Lakoff's frame semantics and Entman's framing functions to reveal the cognitive architecture of political persuasion.

Why it matters: #

Political discourse sometimes is not about conveying neutral facts, it's about constructing the terms of debate. When a politician frames taxation as "relief" rather than "revenue," or immigration as "invasion" rather than "migration," they're activating entire knowledge structures that determine what questions get asked, who's positioned as hero or villain, and what solutions become thinkable or unthinkable.

The analytical approach: #

This prompt treats political texts as layered systems of meaning-making. It asks the model to work through three levels:

1. Lexical/Semantic: Identify the specific words that evoke which frames (e.g., "war," "burden," "family") and map their conceptual metaphors
2. Functional: Analyze how the text defines problems, assigns blame, makes moral judgments, and proposes solutions—Entman's four framing functions
3. Ideological: Synthesize how these elements combine into a coherent moral system (Lakoff's Strict Father vs. Nurturant Parent models) and shape what becomes politically imaginable

About the Outputs #

Each analysis deconstructs how political texts activate semantic frames, position actors, and tap into moral systems to shape what becomes politically thinkable. Not just "this speech uses war metaphors," but a forensic breakdown of how those metaphors work, what they make salient, what they conceal, how they position beneficiaries and victims, and how they activate pre-existing moral frameworks in the audience. The analysis traces bridging language (phrases that redirect attention between issues) and identifies frame vulnerabilities (where the persuasive architecture is weakest).

Extended Processing Summaries #

Some outputs include an "Extended Processing Summary" section at the end which represents the model's intermediate token generation before producing the final analysis. I include these selectively when they're diagnostically interesting. These summaries are computational artifacts that help assess prompt effectiveness, not evidence of cognition. See [About page] for why a first-person presentation of these summaries is itself a framing choice.

The experiment: #

Can we teach a model to perform the kind of frame analysis that political communication scholars do….identifying what cognitive work it performs, what worldviews it activates, and whose interests it serves?

Let me know what you think, Troy #

Discourse Depot © 2025 by TD is licensed under CC BY-NC-SA 4.0. To view a copy of this license, visit https://creativecommons.org/licenses/by-nc-sa/4.0/

#projects/discoursedepot/about