Scholarlink

Awards to faculty are attracting considerable interest due to their benefits for both academics and society. Faculty members dedicate their efforts to teaching, driven by a commitment to education rather than the pursuit of awards. Student feedback, particularly in online settings, plays a crucial role in evaluating teaching effectiveness. This study addresses the framework for selecting the best faculty by considering online feedback. The implementation of this framework involves utilizing trust-based algorithms to refine matrix factorization, leveraging the online feedback of 68 students on 16 questions across 5 different subjects to construct a robust recommendation system. The results underscored the prominence of the Theory of Computation (TOC) subject across various dimensions and pinpointed question number 16 as a crucial predictor, endorsed by 22 students, with RMSE, MAE, and MSE values of 0.8827, 0.7119, and 0.7792, respectively. Moreover, subjects such as human–machine interface (HMI) and business communication (BC) received higher ratings, whereas Database Systems (DB) and Software Engineering (SE) displayed moderate and variable ratings.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Award Recommendation System Using Trust-Aware Matrix Factorization Method Based on Students’ Feedback

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Zakir Mujeeb Shaikh,
  • Sonal Dipin Patil,
  • Akhtar Ismail Nadaf,
  • Gazala Zuber Shaikh

摘要

Awards to faculty are attracting considerable interest due to their benefits for both academics and society. Faculty members dedicate their efforts to teaching, driven by a commitment to education rather than the pursuit of awards. Student feedback, particularly in online settings, plays a crucial role in evaluating teaching effectiveness. This study addresses the framework for selecting the best faculty by considering online feedback. The implementation of this framework involves utilizing trust-based algorithms to refine matrix factorization, leveraging the online feedback of 68 students on 16 questions across 5 different subjects to construct a robust recommendation system. The results underscored the prominence of the Theory of Computation (TOC) subject across various dimensions and pinpointed question number 16 as a crucial predictor, endorsed by 22 students, with RMSE, MAE, and MSE values of 0.8827, 0.7119, and 0.7792, respectively. Moreover, subjects such as human–machine interface (HMI) and business communication (BC) received higher ratings, whereas Database Systems (DB) and Software Engineering (SE) displayed moderate and variable ratings.