Computational Linguistics

From Text to Structure: Cross-Document Narrative Analysis Using AI-Assisted Semantic Signal Extraction

DOI: https://doi.org/10.5281/zenodo.19470453

We introduce Semantic Signal Analysis (SSA), a computational framework for extracting, linking, and analyzing claims across heterogeneous text corpora. Unlike conventional natural language processing (NLP) approaches that operate at the document or sentence level, SSA models discourse as a network of claims, enabling structural analysis of narratives across documents.

Policy Analysis

Manufactured Authority and Narrative Engineering in Policy Documents

DOI: https://doi.org/10.5281/zenodo.19470618

This report presents a comprehensive computational analysis of Project 2025's flagship policy document, "Mandate for Leadership: The Conservative Promise" (Heritage Foundation, 2023). The analysis draws on a structured dataset of 7,397 text segments drawn from 740 document sections, annotated with rhetorical framing scores, topic classifications, claim typologies, entity sentiment data, and extracted policy prescriptions.