Public Sentiment Overview
View All82%
Overall
Positive Sentiment
- Very Positive42%
- Positive36%
- Neutral10%
- Negative5%
- Very Negative3%
Solutions · Public Intelligence
Know what your community is actually experiencing.
This module answers six questions: what are people discussing, which issues matter, which narratives are accelerating, what changed, where is the change located, and how reliable is the signal.
9
Signal families combined
0-100
Composite mood index
7 / 30d
Trend windows
Versioned
Auditable model weights
Mood index
A composite score that shows its working
The mood index combines representative survey signals, aggregate feedback, issue sentiment, media tone and behavioural indicators. The interface always shows absolute score, trend, velocity and confidence together — and the weights are versioned and auditable, so a change in the number can be traced to a change in the world rather than a change in the model.
- Absolute score alongside 7-day and 30-day trend
- Volatility, so a noisy reading is visibly noisy
- Per-signal-family contribution and confidence
- Model version recorded on every score
Citizen Feedback Trends
View All- Service Satisfaction82%↑ 8%
- Infrastructure68%↑ 5%
- Cleanliness61%↑ 4%
- Safety & Security74%↑ 6%
- Transparency79%↑ 7%
Service Delivery Monitoring
View All78%
Overall
Service Index
- On-Time Delivery81%
- Quality of Service76%
- Resolution Rate74%
- Citizen Reach79%
Intelligence functions
What the module computes
Topic & issue extraction
Maps free text and speech onto a canonical issue taxonomy, and surfaces emerging topics that do not yet fit one.
Sentiment & emotion
Aggregate polarity, emotion mix and the velocity at which either is moving — never an individual-level score.
Narrative clustering
Groups semantically related narratives and tracks their size and trajectory over time.
Anomaly detection
Flags unexpected spikes, drops or geographic concentrations that a rolling average would hide.
Propagation analysis
Shows origin and relay patterns across channels and communities, so you can see where something started.
Confidence scoring
Weighs source quality, sample coverage, geographic resolution and model certainty into a single stated confidence.
Input sources
Where the signal comes from
No single source is trusted on its own. Survey data calibrates the noisier digital and community signals, and the difference between them is itself a useful indicator.
| Source | How it is handled |
|---|---|
| Representative surveys | Sample design, weighting and field dates travel with the result |
| Field and mobile surveys | Offline capture with GPS, enumerator ID and resumable sync |
| Citizen feedback and grievances | Every channel normalised into one traceable intake |
| Field worker voice and text reports | Transcribed, classified and linked to a geographic unit |
| Community discussions | Aggregate analysis only, where consent and terms permit |
| Media metadata and transcripts | Print, broadcast, radio and digital news |
| Public web and search signals | Trend indicators, never individual-level tracking |
| Event and outreach feedback | QR, app, voice and manual capture at the point of contact |
Confidence
Why a high-resolution dashboard must not imply certainty
A detailed map of a district with three data points behind it is more dangerous than no map at all. Every score Civiq.plus exposes carries confidence and provenance.
| Contributor | What it measures |
|---|---|
| Freshness | How recently the underlying signals arrived |
| Survey coverage | Whether representative sampling exists for this geography |
| Field reporting | Volume and distribution of field worker reports |
| Community coverage | Breadth of registered community participation |
| Media coverage | Density of media signal for the topic and place |
| Source diversity | How many independent signal families agree |
| Model confidence | The model's own certainty for this classification |
Ready to transform civic outcomes?
See how Civiq.plus can help your teams make better decisions, faster.