cognitive-signal 0.1.0

Orthogonal cognitive signal extraction and pattern detection from journal entries. Extracts valence, arousal, agency, self-focus, social orientation, and action ratio as independent signals, then discovers temporal trends, semantic drift, latent psychological states, and structural change points.

cognitive-signal

Extract orthogonal cognitive signals from journal entries.

Installation

pip install cognitive-signal

Download the spaCy model:

python -m spacy download en_core_web_sm

Quick Start

from datetime import datetime
from cognitive_signal import SignalDetectionPipeline, JournalEntry

# Create journal entries
entries = [
    JournalEntry(
        text="I felt empowered today. Made a big decision at work.",
        timestamp=datetime(2024, 1, 1),
        entry_id="1"
    ),
    JournalEntry(
        text="Worried about the consequences. Maybe I was too hasty.",
        timestamp=datetime(2024, 1, 2),
        entry_id="2"
    ),
    JournalEntry(
        text="Talked to my team and we aligned on the approach.",
        timestamp=datetime(2024, 1, 3),
        entry_id="3"
    ),
]

# Run the pipeline
pipeline = SignalDetectionPipeline()
result = pipeline.process_journal(entries)

# Access signal values
for entry_id, signal in result.signals.items():
    print(f"Entry {entry_id}:")
    print(f"  Valence: {signal.valence:.2f}")
    print(f"  Arousal: {signal.arousal:.2f}")
    print(f"  Agency: {signal.agency:.2f}")

# Temporal trends
for signal_name, trend in result.temporal_trends.items():
    print(f"{signal_name}: slope={trend.slope:.3f}, direction={trend.direction}")

# HMM states
print(f"States: {result.segmentation.states}")
print(f"Phases: {result.segmentation.phases}")

# Change points
for cp in result.change_points:
    print(f"Change at index {cp.index}: {cp.signals_changed}")

The 7 Signals

Signal	Description
Valence	Emotional polarity from negative (-1) to positive (+1)
Arousal	Activation level from calm (0) to excited (1)
Agency	Internal locus of control vs. external attribution
Self-Focus	First-person singular pronoun density
Social Orientation	References to others and relationships
Temporal Orientation	Focus on past, present, or future
Action Ratio	Verb density indicating action vs. reflection

Processing Layers

1. Signal Extraction - Extract 7 orthogonal cognitive signals from raw text
2. Temporal Analysis - Detect trends, slopes, and momentum in signals over time
3. Semantic Motion - Track drift in embedding space and identify thematic shifts
4. HMM Segmentation - Discover latent psychological states using Hidden Markov Models
5. Change Point Detection - Identify structural breaks in signal patterns

Layer 1.5: Dissonance Detection

Between signal extraction and temporal analysis, dissonance detection identifies contradictions:

• Valence-Agency Dissonance: Positive emotions but low agency (or vice versa)
• Self-Social Dissonance: High self-focus combined with high social orientation
• Temporal Dissonance: Conflicting temporal orientations within same entry
• Action-Reflection Dissonance: High action words but reflective/uncertain tone

License

MIT