Automated Teacher Behavior Inventory Management System with AI-Driven Recommendations

Abstract

The Automated Teacher Behavior Inventory Management System with AI-Driven Recommendations was developed to address the challenges encountered by Silay Institute in conducting effective teacher evaluations. This developmental research aimed to design, implement, and assess a system that automates survey-based data collection and analysis, thereby improving accuracy, operational efficiency, and professional growth opportunities for educators. The system evaluates teacher performance based on six key dimensions: Subject Matter Competence, Teaching Styles, Personality Traits, Classroom Management, Learning Assessment, and Overall Impression, following established behavioral frameworks [2]. Leveraging Python’s Pandas library for data analysis and the OpenAI API for AI-generated insights, the system provides personalized recommendations for faculty development workshops and activities [1]. These recommendations can be generated both online through API access and offline using preloaded datasets to ensure continuous functionality during internet outages. This dual-mode design supports uninterrupted access to evaluation results and aligns with institutional goals for integrating technology in educational leadership [3]. User feedback was collected from 30 respondents, including students and faculty members, who rated the system across 15 performance indicators using the Pomel Scale. The results indicated high ratings in user-friendliness, accuracy, interactivity, and operability, demonstrating the system’s effectiveness and reliability. Moreover, the built-in recommendation deduplication mechanism ensured relevance and uniqueness in AI-driven suggestions. The successful implementation of the system significantly streamlined the teacher evaluation process, offering a sustainable and data-driven approach to professional development in higher education [4].