A powerful opinion-analysis tool that evaluates how closely an individual aligns with a specific statement using public social media evidence. This scraper delivers structured insights, relevance-weighted scoring, and a final aggregated stance score to help users understand opinion trends with clarity.
Created by Bitbash, built to showcase our approach to Scraping and Automation!
If you are looking for opinion-compass-agent you've just found your team — Let’s Chat. 👆👆
The Opinion Compass Agent Scraper identifies and evaluates publicly expressed stances by analyzing posts from major social platforms. It determines whether an individual supports, opposes, or is neutral about a specific statement using contextual, evidence-based scoring. This tool is ideal for researchers, journalists, analysts, and teams working with public sentiment interpretation.
- Collects publicly available posts related to the specified person and opinion.
- Scores each evidence source using Opinion Score (−1.0 to 1.0) and Relevance Score (0.0 to 1.0).
- Aggregates evidence into a final stance score weighted by relevance.
- Generates a structured output with explanations and supporting text.
- Ensures insights are interpretable, comparable, and grounded in contextual data.
| Feature | Description |
|---|---|
| AI-driven stance scoring | Generates an aggregated opinion score from −1.0 to 1.0. |
| Evidence evaluation | Assesses each evidence item for both stance intensity and topic relevance. |
| Multi-source opinion extraction | Retrieves opinion-related signals from major social platforms. |
| Weighted aggregation | Uses evidence relevance to calculate a more accurate final score. |
| Structured output | Returns JSON-formatted analysis ready for dashboards or automation. |
| Field Name | Field Description |
|---|---|
| person | The individual whose stance is being analyzed. |
| opinion | The specific statement or claim being evaluated. |
| evidence[].source | Platform where the supporting/contradicting post was found. |
| evidence[].score | The stance score from −1.0 to 1.0 for that evidence. |
| evidence[].relevance | Numerical relevance score from 0.0 to 1.0. |
| evidence[].text | Extracted opinion-related content. |
| evidence[].url | Direct link to the referenced evidence. |
| aggregated.score | Final weighted stance score. |
| aggregated.explanation | Narrative insight explaining how the score was derived. |
{
"analysis": {
"person": "Tomio Okamura",
"opinion": "Democratic values are important.",
"score": 0.5,
"explanation": "The score reflects evidence suggesting the person identifies with the opinion. It ranges from -1.0 to 1.0."
}
}
Opinion Compass Agent/
├── src/
│ ├── runner.py
│ ├── analysis/
│ │ ├── aggregator.py
│ │ ├── scorer.py
│ │ └── relevance_engine.py
│ ├── collectors/
│ │ ├── twitter_collector.py
│ │ └── instagram_collector.py
│ ├── utils/
│ │ └── text_cleaner.py
│ └── config/
│ └── settings.json
├── data/
│ ├── samples/
│ │ └── sample_input.json
│ └── evidence_example.json
├── requirements.txt
└── README.md
- Policy researchers compare public figures’ alignment with political values to support analytical reports.
- Marketing teams analyze influencer alignment with brand messaging to improve outreach decisions.
- Journalists verify stance trends before publishing context-dependent news stories.
- Analysts track shifting sentiment around key statements across different communities.
- Academic researchers study opinion evolution using evidence-based scoring.
How accurate is the stance score? The score reflects the most recent and relevant publicly available evidence. While the model is highly capable, results should be interpreted as analytical guidance, not absolute truth.
Can I analyze any individual? Yes, as long as their content is public and ethically accessible for opinion-based analysis.
Does it support multiple opinions at once? Each run processes one person and one statement. To analyze multiple opinions, run separate requests.
How long does analysis take? Most evaluations complete within a few minutes, depending on data volume and evidence complexity.
Primary Metric: Average analysis completion time: 2–4 minutes for a typical query with 5–15 evidence points.
Reliability Metric: Consistent evidence retrieval success rate above 97% across supported platforms.
Efficiency Metric: Optimized relevance-weighting pipeline processes evidence with minimal overhead, maintaining stable performance even with expanding datasets.
Quality Metric: Aggregated scores maintain high interpretability, with evidence explanations covering 95%+ of contributing factors clearly.
"Bitbash is a top-tier automation partner, innovative, reliable, and dedicated to delivering real results every time." Nathan Pennington
|
"Bitbash delivers outstanding quality, speed, and professionalism, truly a team you can rely on." Eliza
|
"Exceptional results, clear communication, and flawless delivery. Syed
|