Recommender systems (RSs) are becoming widespread in diferent application domains to provide personalized items to given service users. Because of such an increasing adoption of RSs, it is becoming urgent to define a precisely curated and organized core set of concepts and practices, i.e., a Body of Knowledge (BOK), as already done in other disciplines, including software engineering and model-driven engineering. The opportunities related to the availability of an RSBOK are manifold, and diferent stakeholders would benefit from it including, developers, teachers, and newcomers to the RS community. Further than motivating a BOK for recommender systems and discussing corresponding envisioned opportunities and challenges, we also propose a methodology that can be employed to support the definition of an RSBOK.
was defined with diferent goals, including “ 1)
promoting a consistent view of software engineering worldwide;
Recommender systems (RSs) are complex software sys- 2) specifying the scope of, and clarify the place of
softtems that can provide users with relevant items of inter- ware engineering with respect to other disciplines [. . . ]; 3)
est for the particular application domains and contexts characterizing the contents of the software engineering
dis[
While RSs are becoming ubiquitous, we believe that it and practical tools and techniques coming from the SLE
is necessary to ensure that the next generation of engi- field ” [
To the best of our knowledge, SWEBOK is the first pline and to support various activities including training
body of knowledge that was conceived for characteriz- and the development of new technologies and tools.
ing the software engineering discipline [
Altogether, this is expected to come in handy for those who work as recommender systems designers.
– Languages to be adopted: To make the definition and tools to widen and simplify the adoption of RSs in any complex software systems. The knowledge encoded in the envisioned RSBOK framework can help developers, among others, to distill the algorithms that should be made available to ifnal users. – Teachers: They are researchers, practitioners, and educators in general who are in charge of training new generation of professionals in the design, development and operation of new RSs. To this end, RSBOK can be used as a reference point, e.g., to link code examples, textual explanations, experiences, RS usage and development best practices, and code examples that demonstrate the usage of
RS technologies. – Contributors: These users correspond to RSs developers, and adopters who are willing to extend the knowledge formalized in RSBOK.
Despite their enormous popularity and the remarkable
performance that recommender systems have achieved in
recent years, one of the long-standing problems afecting
the performance of these systems concerns the sparsity of
interactions between users and items. Over the past years,
recommender system designers have relied on additional
sources of information to overcome this issue. Modern
RSs combine collaborative information with metadata
(e.g., tags, reviews), social connections, image and audio
signal-derived features, and contextual data [
The RSBOK definition is indeed a community efort to the design and development of the diferent RSs
develformalize and share knowledge from diferent stakehold- oped in the context of the EU CROSSMINER project [
ers, who are interested in conceiving techniques
and the usage of RSBOK homogenous, it is necessary to decide the languages and tools that need to be adopted. Feature diagrams, Ecore models, and OWL ontologies are only examples of possible notations that might be employed to formalize the results of the conceptualization eforts. – Realization process: By looking at the ways other
BOKs have been developed, we believe that we need a community efort, which has to be performed by following precise protocols, moderation mechanisms, quality check procedures, to name a few. In this respect, it is of great importance to support contributions that may come from diferent stakeholders. Consequently, to keep the quality of the resources under control, it is necessary to define processes and setup tools for moderating the diferent contributions and to make sure that they are all homogenized. – Engagement: Even though the RSs opportunities can be convincing, they might not be enough to engage people in concretely contributing with the RSBOK definition and managing its whole lifecycle. To facilitate a clear understanding of the fundamental techniques and tools underpinning the development and usage of RSs, in this paper we envisaged the core concepts, mechanisms, and practices related to the development and use of RSs. We aim to foster RSBOK, an RS Body of Knowledge definition to formalize and characterize the Recommender System domain.
For future work, we plan to tackle the challenges mentioned in Section 3. In particular, it is necessary to put into efect the conceived paradigm by realizing its constituent components. Among others, we will investigate and select suitable tools and languages, attempting to make the definition and usage of RSBOK homogeneous.