Recommender systems serve as mediators of information consumption and propagation, leveraging the massive volume of user-generated content to deliver relevant and engaging suggestions. In this role, these systems have recently criticized for introducing biases and promoting the creation of echo chambers and filter bubbles, thus lowering the diversity of content users are exposed to as well as potentially new social relations. Some of these issues result are a consequence of the fundamentals concepts on which recommender systems are based. Assumptions like the homophily principle (according to which similar users tend to be interested in similar items) might lead users to content that they already like or friends they already know, can be naïve in the era of ideological uniformity and fake news. A significant challenge in this context is how to effectively learn the dynamic representations of users based on the content they share and their echo chamber or community’s interactions to recommend potentially relevant and diverse friends from outside the network of influence of users’ community. To address this, we devise FRediECH (A Friend RecommenDer for breakIng Echo CHambers), an echo chamber-aware friend recommendation approach that learns users and echo chamber representations from the shared content and past users’ and communities’ interactions. Comprehensive evaluations over Twitter data showed that our approach achieved better performance (in terms of relevance and novelty) than state-of-the-art alternatives, validating our approach’s effectiveness.