Nowadays a recommendation model should exploit additional information from both the user and item perspectives, in addition to utilizing user-item interaction data. Datasets are central in offering the required information for evaluating new models or algorithms. Although there are many datasets in the literature with user and item properties, there are several issues not covered yet: (i) it is difficult to perform cross-analysis of properties at user and item level as they are not related in most cases; and (ii) on top of that, in many occasions datasets do not allow analysis at different granularity levels. In this paper, we propose a new dataset in the music domain, named AMBAR, that tackles the above-mentioned issues. Besides detailing in depth the structure of the new dataset, we also show its application in contexts (i.e., multi-objective, fair, and calibrated recommendations) where both the effectiveness and the beyond-accuracy perspectives of recommendation are assessed.

Educational recommender systems channel most of the research efforts on the effectiveness of the recommended items. While teachers have a central role in online platforms, the impact of recommender systems for teachers in terms of the exposure such systems give to the courses is an under-explored area. In this paper, we consider data coming from a real-world platform and analyze the distribution of the recommendations w.r.t. the geographical provenience of the teachers. We observe that data is highly imbalanced towards the United States, in terms of offered courses and of interactions. These imbalances are exacerbated by recommender systems, which overexpose the country w.r.t. its representation in the data, thus generating unfairness for teachers outside that country. To introduce equity, we propose an approach that regulates the share of recommendations given to the items produced in a country (visibility) and the position of the items in the recommended list (exposure).

Recommender systems are key tools to push the consumption of items. Imbalances in the data distribution might affect the exposure given to providers, thus affecting their business and experience in the platform. In my work, I study the impact of data imbalances for the stakeholders, according to how recommendations are generated.