Technology Enhanced Learning (TEL) is emerging as a popular learning approach utilized by both educational institutions and business organizations. Learning Recommender Systems (RSs) can help e-learners to cope with the data overload difficulty and suggest useful items that users may wish to use. This research aims to examine the design and implementation of personalized RS that supports individual learning in the workplace. First, a hybrid knowledge recommendation technique is proposed by combing content-based method with feedback learning method to adapt to the dynamic preference of users. Second, the design and implementation of a personalized knowledge recommender system using proposed technique in a case company is presented. Quantitative and qualitative data are collected to validate the system and evaluate its performance and impact. The preliminary results show that involving enterprise experts and target users in the system design phase can improve the system transparency and users’ trust in the system. It is also found that users’ learning attitude can be positively influenced by the system experience. This research provides important implications on employing intelligent recommender system to support workplace learning.
Shuang, Geng; Li, Chen; Yue, Feng Yuan; Jing, Tan Li; Ben, Nim; and Jia, Liu, "A Personalized Knowledge Recommender System For Workspace Learning" (2018). CONF-IRM 2018 Proceedings. 17.