The interaction between teachers and students plays a crucial role in the learning process. However, differences between them may hinder effective communication and compromise learning outcomes. To address this, a personality-aware recommendation system, the Hybrid Personality Model (HPM), is proposed. Hybrid filtering techniques and the Big Five personality traits are utilized by the system to match students with teachers who share similar personalities. To evaluate the effectiveness of HPM, a comparison was conducted with two other recommendation systems: Birds of a Feather (BOF), a knowledge-based system, and Collaborative Filtering (CF). The results indicate that while CF outperforms HPM in terms of precision in most scenarios, HPM demonstrates greater robustness in handling data sparsity, as evidenced by a less significant drop in recall and F-score when using a limited number of recommendations (k=3). This research shows that the proposed system can be applied consistently in educational environments