Enhancing Employee Attention and Task Efficiency Using Advanced Digital Distraction Blocking Mechanisms

Employee attention is critical for successful task completion, learning, and productivity. However, modern distractions such as notifications, applications, and online information regularly disrupt focus and reduce work effectiveness. Research aims to improve employee attention and task efficiency by creating an advanced digital distraction blocking system that detects distracted behaviors and intervenes to maintain focus. Video recordings of employees executing tasks in online and digital settings were gathered to capture natural attention and distraction patterns. Frames were normalized, faces were identified, and irrelevant background noise was eliminated to ensure consistent data quality. Frame blocking is utilized for preprocessing, and the VGG16-CNN was used to extract deep visual features, including facial expressions, gaze direction, head orientation, and micro-movements that indicate attentiveness or distraction. A Decision Tree Tuned Scalable Spiking Network (DT-S2Net), which combines Decision Trees (DT) for interpretable classification with Scalable Spiking Neural Networks (S2NN) for temporal pattern detection of attention and distraction behaviors. The DT-S2Net method outperformed the existing methods, achieving higher accuracy (99.01%), precision (99.57%), recall (98.77%) and F1-score (99.0%) in recognizing distracted states, allowing for timely digital interventions such as limiting notifications or irrelevant programs, resulting in faster task completion and sustained focus.