Recommender systems have become one of the main tools for personalized content filtering in the educational domain. Those who support teaching and learning activities, particularly, have gained increasing attention in the past years. This growing interest has motivated the emergence of new approaches and models in the field, in spite of it, there is a gap in literature about the current trends on how recommendations have been produced, how recommenders have been evaluated as well as what are the research limitations and opportunities for advancement in the field. In this regard, this paper reports the main findings of a systematic literature review covering these four dimensions. The study is based on the analysis of a set of primary studies (N = 16 out of 756, published from 2015 to 2020) included according to defined criteria. Results indicate that the hybrid approach has been the leading strategy for recommendation production. Concerning the purpose of the evaluation, the recommenders were evaluated mainly regarding the quality of accuracy and a reduced number of studies were found that investigated their pedagogical effectiveness. This evidence points to a potential research opportunity for the development of multidimensional evaluation frameworks that effectively support the verification of the impact of recommendations on the teaching and learning process. Also, we identify and discuss main limitations to clarify current difficulties that demand attention for future research.