Methodology

How SignalWatch Works

SignalWatch is a predictive linguistics system that monitors online communities to detect early signals of emerging events. It combines eight detection hypotheses with community-tier tracking and historical analog matching to forecast how nascent narratives will evolve.

Core Pipeline
From raw text to actionable forecast in four stages
Ingest

We poll diverse sources — Hacker News, Bluesky, Mastodon, Arctic Shift, and RSS feeds — continuously. Each source is assigned a community tier (niche expert, enthusiast, or mainstream) based on its audience composition.

Analyze

Incoming text is evaluated against our eight hypotheses by a large-language-model analyst. Each hypothesis is scored for confidence, and the system extracts specific linguistic markers, escalation indicators, and a time-horizon estimate.

Track

When a signal is detected, we begin tracking its strength over time, its trajectory (accelerating, peaking, stable, decelerating, or fading), and its spread across community tiers. Signals that reach Tier 2 or Tier 3 gain analytic priority.

Forecast

Active signals are matched against a historical archive of resolved events (e.g., the SVB collapse, the GME squeeze, Brexit). The prediction engine assigns probability distributions to resolution archetypes and generates observable confirmation indicators.

Signal Strength
A 0–100 composite score
0 – 25Dormant
26 – 50Emerging
51 – 75Active
76 – 100Critical

Strength is derived from hypothesis confidence, community tier spread, velocity of mentions, and sentiment intensity. A signal reaching Critical does not mean certainty — it means the narrative is moving fast and widely.

The Eight Hypotheses

Every piece of text SignalWatch analyzes is scored against these eight hypotheses. A single text may trigger multiple hypotheses. The more hypotheses firing with high confidence, the stronger the overall signal.

Narrative Contagion

Same story or frame appearing across ideologically different communities. We look for cross-community linguistic convergence — shared framing that transcends normal echo chambers. When a narrative jumps from niche experts to enthusiasts to mainstream, it signals a true cultural shift rather than a siloed trend.

Typical markers
  • cross-community terminology overlap
  • shared hashtags across political divides
  • same frame in financial + tech + health spaces
Anomalous Velocity

Niche, technical, or domain-specific vocabulary appearing at unusual frequency — words specialists use before journalists abstract them. A sudden spike in jargon out of its normal context often precedes mainstream coverage by weeks.

Typical markers
  • domain jargon in general forums
  • technical terms in non-technical communities
  • expert language trending on social platforms
Sentiment Divergence

A widening gap between official or institutional framing and grassroots emotional expression. When people express distrust of the official narrative, or emotional tone contradicts stated facts, the ground is shifting beneath the consensus.

Typical markers
  • media says calm / comments say panic
  • institutional framing vs. community anger
  • official stats contradicted by lived experience stories
Metaphor Shift

The dominant metaphors people use to describe something have changed. Home as investment becomes home as trap. Crypto as future becomes crypto as casino. Work as career becomes work as survival. Metaphor shifts precede behavioral shifts.

Typical markers
  • new dominant metaphor emerging in discourse
  • old metaphor used ironically or rejected
  • metaphor crosses from one domain to another
Question Frequency Curve

What stage of the adoption or disillusionment cycle do the questions indicate? 'What is X' = early. 'How do I X' = growth. 'Why did X fail' = disillusionment. 'How do I recover from X' = bottom. We map the question landscape to identify cycle position.

Typical markers
  • shifting from what → how → why → recovery
  • questions becoming more emotional
  • advice requests peaking then declining
Emotional Valence Asymmetry

High engagement volume but suppressed or neutral emotional expression. People are clearly engaged but not expressing feeling — a tension state that can precede sharp sentiment reversals in either direction.

Typical markers
  • high engagement, flat sentiment scores
  • measured language in emotional situations
  • suppressed reactions before a floodgate opens
Institutional Language Lag

Technical or grassroots vocabulary that institutions have not adopted yet. When community language precedes institutional language, policy, regulation, and market response are typically 12–24 months behind.

Typical markers
  • regulators using outdated terminology
  • mainstream media lacking vocabulary for a trend
  • institutions reacting to language from 1–2 years ago
Exhaustion Signature

Catastrophizing or intense language that appears to be peaking or declining into disengagement. Exhaustion often precedes bottoms. Disengagement from a crisis narrative often precedes recovery or a new equilibrium.

Typical markers
  • peak catastrophizing followed by silence
  • people expressing burnout about a topic
  • former activists shifting to resignation or apathy

Limitations & Uncertainty

SignalWatch is a probabilistic tool, not a crystal ball. It can detect patterns that historically preceded major events, but correlation is not causation. False positives occur — a signal may fade without ever resolving into a headline event. The system is designed to surface narratives early, which means it will sometimes be wrong. That is the trade-off of early detection: higher recall, lower precision. Every forecast includes a confidence note and a list of what would confirm or invalidate the prediction.