Skip to content

Anyma-exe/attention-flow

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

AttentionFlow

Ecological Measurement of Attentional Variability

A Python-based tool for measuring attention in real-life contexts, combining objective behavioral data with subjective self-report measures.

Python Streamlit License Field

Research Context

Traditional attention assessments are conducted in controlled laboratory settings, which limits their ecological validity. AttentionFlow addresses this gap by measuring attentional performance in naturalistic, everyday contexts using an Ecological Momentary Assessment (EMA) approach.

Research question:

"How does attention fluctuate in ecological contexts?"

Hypothesis: Higher intra-individual variability (IIV) in reaction times reflects lower attentional stability — consistent with current computational models of ADHD.


What It Measures

Measure Neuro-Cognitive Significance
RT Mean Processing speed index
Intra-individual variability (IIT) Attentional stability & neural noise indicator
Time-of-day fluctuations Circadian rythm impact on executive functions
Inhibition errors Missed or delayed responses
Subjective attentional profile Self-report scores across 3 dimensions

Project Structure & Logic

The project is organized into modular components to separate data collection, processing and visualization.

Core Methdology: Ecological Momentary Assessment (EMA)

Unlike traditional lab tests, AttentionFlow captures attention in "the wild" to ensure ecological validity.

Unpredictability : Stimuli are sent at random intervals to capture real-state attentional focus, not task-preparedness.

Multidimensional Metrics :

  • Objective: Reaction Time (RT), Intra-individual Variability (IIV), and notification response latency.

  • Subjective: A 11-item self-assessment questionnaire inspired by clinical frameworks (Inattention, Hyperactivity, Impulsivity).

Analytical Goal : Correlating behavioral variability with subjective self-perception to identify cognitive patterns or subjective biases.

Advanced Data Visualization

The integrated dashboard provides three key research-grade visualizations:

1. Temporal Fluctuations : Line charts showing performance evolution across the day (morning vs. evening fatigue).

2. IIV Distribution : Distribution plots showing the "neural noise" or stability of the attentional system.

3. Consistency Analysis : Comparison between the Subjective Attentional Profile and Objective Behavioral Data.

Non-Clinical Disclaimer : This tool is designed for research and self-exploration purposes only. It does not constitute a medical diagnosis. The questionnaire is an educational adaptation of clinical logic.

Installation

Requirements: Python 3.10+

git clone https://github.com/yourusername/attentionflow.git
cd attentionflow
pip install pandas streamlit matplotlib seaborn plyer

sudo apt-get install python3-tk libnotify-bin

python collector/main.py

streamlit run dashboard/app.py

Dashboard Features
Reaction time over trials — visualizes attentional fluctuations
Distribution of reaction times — shows intra-individual variability
Heatmap by hour of day — identifies peak attention periods
Automatic interpretation — CV-based variability classification
Self-assessment questionnaire — 11 items across 3 dimensions
Subjective vs. objective comparison — cross-validates both measures

Self-Assessment
The questionnaire is a non-clinical self-report tool inspired by
attentional dimension frameworks (inattention, hyperactivity, impulsivity).
It uses a 5-point Likert scale and covers 11 items across 3 dimensions.
This tool does not constitute a clinical diagnosis.
If you have concerns about your attention, please consult a qualified professional.

Limitations
Task conditions are not experimentally controlled
Sample size is limited to individual self-measurement
Notification delivery depends on system and OS configuration
Self-report measures are subject to subjective bias
Results are exploratory and cannot be generalized

Theoretical Background
This project draws on the following frameworks:
Ecological Momentary Assessment (EMA) — Shiffman et al. (2008)
Intra-individual variability (IIV) — Castellanos et al. (2005)
Computational models of ADHD — Sikström & Söderlund (2007)
Reaction time variability as ADHD marker — Hervey et al. (2006)

Author
Built as a personal research project exploring the intersection of cognitive neuroscience, computational modeling, and ecological measurement.
L2 Psychology — Master's candidate in Cognitive Neuroscience

About

A Python tool for Ecological Momentary Assessment (EMA) of attentional variability.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages