# akashmurugesan-datascientist/geo-bias-in-llm architecture

> Architecture diagram of the GitHub repository akashmurugesan-datascientist/geo-bias-in-llm, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-02). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/akashmurugesan-datascientist/geo-bias-in-llm
- Repository: https://github.com/akashmurugesan-datascientist/geo-bias-in-llm

## Overview

This repository is a dissertation analysis project, not a deployed application. Its principal workflow compares air-quality measurements, public perceptions and labeled LLM responses, with the combined proxy dataset supporting final comparison and visualisation. The README documents the notebook’s preparation, analysis and visualisation role and names the data artifacts; no source excerpts were available, so the graph avoids claiming specific notebook operations or an exact processing order.

Main entry points: [`Geo_Bias_in_LLM.ipynb`](https://github.com/akashmurugesan-datascientist/geo-bias-in-llm/blob/main/Geo_Bias_in_LLM.ipynb) (Analysis notebook), [`ground_truth_monthly_with_aqi.csv`](https://github.com/akashmurugesan-datascientist/geo-bias-in-llm/blob/main/ground_truth_monthly_with_aqi.csv) (Air quality and AQI), [`perception_summary_monthly_complete.csv`](https://github.com/akashmurugesan-datascientist/geo-bias-in-llm/blob/main/perception_summary_monthly_complete.csv) (Public perception), [`llm_outputs_labeled.csv`](https://github.com/akashmurugesan-datascientist/geo-bias-in-llm/blob/main/llm_outputs_labeled.csv) (Labeled LLM responses)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_inputs["Analysis inputs"]
  node_air_quality["Air quality and AQI"]
  node_public_perception["Public perception"]
  node_llm_responses["Labeled LLM responses"]
end

subgraph group_analysis["Analysis workflow"]
  node_notebook["Analysis notebook"]
end

subgraph group_results["Comparison results"]
  node_proxy["Comparison dataset"]
  node_dissertation["Dissertation findings"]
end

node_air_quality -->|"analysis input"| node_notebook
node_public_perception -->|"analysis input"| node_notebook
node_llm_responses -->|"analysis input"| node_notebook
node_proxy -->|"final comparison input"| node_notebook
node_notebook -->|"supports findings"| node_dissertation

click node_air_quality "https://github.com/akashmurugesan-datascientist/geo-bias-in-llm/blob/main/ground_truth_monthly_with_aqi.csv"
click node_public_perception "https://github.com/akashmurugesan-datascientist/geo-bias-in-llm/blob/main/perception_summary_monthly_complete.csv"
click node_llm_responses "https://github.com/akashmurugesan-datascientist/geo-bias-in-llm/blob/main/llm_outputs_labeled.csv"
click node_notebook "https://github.com/akashmurugesan-datascientist/geo-bias-in-llm/blob/main/Geo_Bias_in_LLM.ipynb"
click node_proxy "https://github.com/akashmurugesan-datascientist/geo-bias-in-llm/blob/main/final_perception_proxy.csv"
click node_dissertation "https://github.com/akashmurugesan-datascientist/geo-bias-in-llm/blob/main/Geo-Bias%20in%20LLM.pdf"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_air_quality,node_public_perception,node_llm_responses toneBlue
class node_notebook toneAmber
class node_proxy,node_dissertation toneMint
```

## Components

### Analysis inputs

- [Air quality and AQI](https://github.com/akashmurugesan-datascientist/geo-bias-in-llm/blob/main/ground_truth_monthly_with_aqi.csv): `ground_truth_monthly_with_aqi.csv`
- [Public perception](https://github.com/akashmurugesan-datascientist/geo-bias-in-llm/blob/main/perception_summary_monthly_complete.csv): `perception_summary_monthly_complete.csv`
- [Labeled LLM responses](https://github.com/akashmurugesan-datascientist/geo-bias-in-llm/blob/main/llm_outputs_labeled.csv): `llm_outputs_labeled.csv`

### Analysis workflow

- [Analysis notebook](https://github.com/akashmurugesan-datascientist/geo-bias-in-llm/blob/main/Geo_Bias_in_LLM.ipynb): `Geo_Bias_in_LLM.ipynb`

### Comparison results

- [Comparison dataset](https://github.com/akashmurugesan-datascientist/geo-bias-in-llm/blob/main/final_perception_proxy.csv): `final_perception_proxy.csv`
- [Dissertation findings](https://github.com/akashmurugesan-datascientist/geo-bias-in-llm/blob/main/Geo-Bias%20in%20LLM.pdf): `Geo-Bias in LLM.pdf`

## Connections

- Air quality and AQI → Analysis notebook: analysis input (evidence: `README.md`)
- Public perception → Analysis notebook: analysis input (evidence: `README.md`)
- Labeled LLM responses → Analysis notebook: analysis input (evidence: `README.md`)
- Comparison dataset → Analysis notebook: final comparison input (evidence: `README.md`)
- Analysis notebook → Dissertation findings: supports findings (evidence: `README.md`)
