> ## Documentation Index > Fetch the complete documentation index at: https://learn.social.plus/llms.txt > Use this file to discover all available pages before exploring further. > Enabling safe and engaging live-streaming experiences. # Livestream moderation Real-time automated analysis of live video frames & audio to surface or auto-enforce against policy violations with minimal latency. Use this guide to enable, configure thresholds, act on incidents, and continuously tune signal quality. ## Enable the Feature Contact support to enable livestream moderation. Support confirms activation; feature appears in Console settings. First 1–2 weeks: log results but keep automatic termination conservative. Provision & price Per-category thresholds Status & incident volume Stop / Delete streams Threshold calibration Review false positives ## How Detection Works The system continuously samples frames (and audio signals where applicable) and classifies content into risk categories. Each detection produces category confidence scores (0–100%). Your configured thresholds decide whether a stream: | Outcome | Trigger | System Action | User Experience | | ---------- | -------------------------------------------------- | ------------------------------------ | ------------------------- | | Pass | All confidences below Flagged thresholds | Continues | Normal playback | | Flagged | Any category ≥ Flagged threshold but \< Terminated | Marked for review (no auto-stop) | Appears normal to viewers | | Terminated | Any category ≥ Terminated threshold | Broadcast stopped; post soft‑deleted | Appears as normally ended | ## Detection Categories Explicit sexual imagery/acts. Maintain strict thresholds to minimize exposure risk. Graphic violence or severe physical harm. Sensitivity may vary by regional norms. Illegal / compliance restricted material (e.g., weapons, contraband). Low tolerance. Borderline or contextual material. Often noisier—calibrate carefully to reduce review overload. Offensive language or slurs (audio/overlays). Tune to community standards. ## Configuring Confidence Thresholds Two thresholds per category: Flagged (human review) and Terminated (auto-stop). Flagged \<= Terminated must always hold. Flagged 40% · Terminated 75% (balanced starting point). Lower thresholds catch more violations (higher recall) but increase noise (lower precision). Raise thresholds to reduce false positives. Collect 1–2 weeks of incidents → Measure False Positive Rate (FPR) & Misses → Adjust ±5–10% → Re-evaluate. Log each change: date, category, old/new values, rationale, reviewer. A threshold of 0 (or extremely low) will flood the queue with low-confidence matches, overwhelming moderators and increasing costs. ## Tuning Playbook Flag queue FPR > 30% or moderator backlog growing & SLA breach risk. Confirmed late detections or missed early intervention opportunities. Any unjustified auto-termination (precision drop) or creator complaints validated. Severe violations frequently only reaching Flagged state; evidence of slow manual response. Temporarily widen only the lowest-signal category (e.g., Inappropriate) while holding strict categories steady. ## Acting on Incidents Open flagged stream → verify frame samples → Decide: Stop, Delete, or Allow. Graceful end; keeps audit trail; use for policy breach requiring immediate halt. Soft-deletes post & disables playback; apply for severe / disallowed content. Multiple terminations from same broadcaster → review account history & consider broader enforcement. Each false positive or miss → capture category & confidence to feed tuning log. ## Key Metrics | Metric | Definition | Target / Signal | Action Trigger | | ----------------------------- | ------------------------------------------- | --------------------------- | ---------------------------------------------------------- | | Flag Volume per Hour | Flagged streams / hour | Baseline after Week 1 | Sustained spike → investigate attack/content trend | | False Positive Rate (Flagged) | (Flags cleared as OK) / Flags reviewed | \< 30% | Higher → raise Flagged threshold | | Termination Precision | Valid terminations / Total terminations | > 95% | Drop → raise Terminated threshold & audit samples | | Miss Incidents | Confirmed violations not flagged/terminated | 0 critical misses | Any miss → lower relevant thresholds or escalate model gap | | Avg Review Time | Time from flag to moderator decision | Within SLA (e.g., \< 5 min) | Rising trend → staffing or threshold adjustment | | Category Distribution | % flags by category | Stable pattern | Sudden skew → targeted abuse or threshold imbalance | ## Best Practices Run with only Flagged actions (no Terminated) for initial calibration if risk appetite allows. Adjust one category per cycle to attribute impact. Retain representative false positives & misses for model feedback. Provide clear examples per category to align decisions & reduce subjective variance. Publish community guidelines emphasizing live content do's & don'ts. ## Troubleshooting | Issue | Likely Cause | Resolution | | -------------------------------- | ------------------------------------------------------- | -------------------------------------------------------------------- | | Overloaded Flag Queue | Flagged threshold too low / spike event | Raise threshold 5% or add temporary staffing; isolate noisy category | | Repeated False Terminations | Terminated threshold aggressive or misclassified scenes | Increase threshold; review sample frames; report to support | | Missed Severe Violation | Threshold too high or model blind spot | Lower thresholds; capture evidence & escalate for model improvement | | Cost Surge | Increased broadcast minutes + high flag rate | Audit usage, enforce creator guidelines, optimize thresholds | | Inconsistent Moderator Decisions | Lack of unified rubric | Establish decision matrix & training refresh | | Slow Review Times | Understaffing or UI overload | Add shift coverage; refine filters; raise thresholds temporarily | ## Next Steps Central triage & audit Broadcaster behavioral context