Authors
Keywords
Abstract
Abstract: This research provides a comprehensive evaluation of an automated label detection and recommendation system that uses the Statistical Package for the Social Sciences (SPSS) for analysis. It focuses on the development and validation of an intelligent system designed to automatically identify and recommend labels in various domains such as software requirements specifications (SRS), medical imaging, customer feedback, and other related applications. To improve detection accuracy and operational efficiency, the system uses advanced machine learning models; specifically deep convolution neural networks (CNNs).The evaluation followed a multivariate framework that included six input parameters: content type, document source, language, topic, author role, and intended audience. The system performance was measured using five primary criteria: label accuracy, relevance, context alignment, clarity, and confidence in automation. A sample of 10 participants was used to conduct the analysis in SPSS, and to apply reliability testing, descriptive statistics, and correlation methods. The findings showed strong internal consistency, with Cronbach’s alpha values ranging between 0.604 and 0.820, indicating acceptable to high reliability. The mean scores from the descriptive statistics ranged between 3.20 and 4.00 across all scales, with the fit score being the highest (4.00) and the clarity score the lowest (3.20). The correlation results revealed very high positive relationships between the variables (r = 0.891–1.000, p < 0.01), reflecting consistent user perceptions across the evaluation scales.
The system excelled in particular in label accuracy and automation confidence, both showing near-perfect correlation values (r = 1.000). However, clarity stood out as a key area for improvement, showing the largest variance and lowest mean rating. Overall, the results highlight the strong performance of the system, but also point to the need to improve clarity and user interface elements to further enhance performance and user satisfaction.This program monitors customer traffic data for critical services at set intervals. It analyzes this data to identify essential services operating within system workloads and generates insights and label suggestions based on their traffic patterns. Additionally, it offers a structured workflow for assigning labels to these workloads and provides policy recommendations aimed at enhancing workload protection.
