Spaces:
Paused
Paused
| title: Discourse & Rhetorical Analyzer | |
| emoji: 🗣️ | |
| colorFrom: indigo | |
| colorTo: purple | |
| sdk: gradio | |
| python_version: "3.10" | |
| app_file: app.py | |
| pinned: false | |
| license: mit | |
| # Discourse & Rhetorical Analyzer | |
| This is a premium, lightweight, interactive Argument Deconstruction and Discourse Connector mapping tool designed specifically for computational social science and humanities courses. | |
| ## Features | |
| - **Flexible Data Input**: Paste raw text directly or upload datasets (`.csv`, `.xlsx`, or `.txt`). | |
| - **Flexible Discourse Parsers**: | |
| - **Local Cue-Based (CPU & Fast)**: Runs a custom rule-based extraction scanning for comprehensive contrast, cause/effect, addition, and conclusion connective markers locally on CPU. | |
| - **Transformers (AI Mode)**: Leverages advanced generative models (like `Qwen2.5`) via Hugging Face's Serverless API with your personal access token to generate rich, claims-evidence logical fallacy trees. | |
| - **Plotly Visualizations**: Displays beautifully balanced pie/bar charts representing the distribution of rhetorical moves (Counterargument, Causation, Elaboration, Synthesis). | |
| - **Interactive Visual Highlighting**: Renders custom color highlights around active rhetorical connectors. | |
| - **CSV Data Export**: Easily export extracted connectors, sentences, and categories as a CSV report. | |