Development of Faculty Data Model and Evaluation System Using Decision Tree and Sentiment Analysis Algorithm
Proceedings of the 13th International Conference on Information Technology: IoT and Smart City, (2026), pp. 188-194
Ace C. Lagman
a
,
Rommel J. Constantino
b
,
Jeneffer A. Sabonsolin
a
,
Laser Ryan V. Lleno
c
,
Ariel A. Dela Cruz
d
,
Mary Ann T. Lim
e
a FEU Institute of Technology, Manila, Philippines
b Bestlink College of the Philippines, Manila, Philippines
c Bestlink College of the Philippine, Manila, Philippines
d Ilocos Sur Polytechnic State College, Ilocos, Philippines
e Dr. Yanga's Colleges, Inc,, Bulacan, Philippines
Abstract: Effective teaching forms the bedrock of education, directly influencing program accreditation and institutional performance. A competitive and supportive learning environment, fostered by strong faculty performance, is crucial for an academic institution to achieve its vision and mission. This study incorporates Sustainable Development Goals (SDGs) principles, ensuring that faculty performance evaluation contributes to long-term educational sustainability. Addressing the pressing need for robust faculty performance assessment, data mining algorithms are employed to extract insightful information regarding effective instruction, utilizing both structured and unstructured data. The developed system aims to empower institutions to identify their strengths, address areas for improvement, and cultivate continuous growth in teaching and learning processes by discerning trends within faculty data. Furthermore, sentiment analysis methods are utilized to evaluate qualitative input, with Laravel 8.0 serving as the framework for algorithm implementation. Expert evaluations of the system yielded a grand mean score of 4.38, deemed 'Very Acceptable,' thereby affirming its reliability and efficacy in supporting faculty performance reviews and advancing SDG objectives.