Recommender Systems produce suggestions to users for items or contents based on user profiles, users’ explicit or implicit feedback, which the users might have not originally considered but might be of interest to them. Such recommendations are produced by analyzing what they previously consumed (bought, watched, or listened) or by the identification of similarities with other users. Such an explicit feedback is usually an expression of extreme ratings, either positive or negative. In the middle of the range stays a set of different actions in the interface that might be interpreted as feedback, but that needs to be collected implicitly. Even if the literature provides different techniques for collecting implicit feedbacks, they are usually tailored to specific types of applications.
From the user’s point of view Recommender Systems remain a black box that suggests objects or contents, but the users hardly understand why some items are included in the suggestion list. Providing the users with an understandable representation of how the system represents them and allowing them to control the recommendation process would lead to benefits in how the recommendations are perceived and in the capability of the system to be persuasive. Such transparency is one of the multiple (and usually conflicting) requirements of Recommender Systems.
Beyond the classical engineering of Recommender Systems focusing on data processing, filtering and sorting, the engineering aspects should also cover aspects related to how users interact with it, including how to input data, how to define and evolve the user model, how to present the information to the users and how the users can manipulate that information. Such engineering processes might benefit from practice in specific areas, such as web configurators (which guide the users in the inspection of possible product variants) and safety critical interactive systems (where predictability and consistency over executions are prerequisite to certification). In order to deploy Recommender Systems in broader contexts, there is a need for structured and systematic approaches to engineer such complex computing systems.
This special issue solicits novel papers on a broad range of topics, including, but not limited to:
- NOVEL APPLICATION DOMAINS
- Critical systems
- 3D, Augmented and Virtual Reality
- End User Development
- Other novel applications
- USER INTERFACES FOR RECOMMENDER SYSTEMS
- Differences and analogies between UIs for recommender systems, expert systems, and configuration systems;
- Identifying and managing conflicts between the properties of the UI and properties of the Recommender Systems;
- Transparency of the recommendation process and creation of interactive handles for supporting user’s control;
- New interactions for consuming and guiding recommendation (gestures, tangible interaction etc.);
- Analysis of feedback based on small exposures on the item itself: photos, trailers etc.
- RECOMMENDER SYSTEMS CORE
- Exploit the user interaction to enrich recommendation models based on latent factors;
- Real time aspects of recommendations: view updates, user’s awareness, balance between recommendation, and task focus/goal, worst case execution time analysis;
- Recommendation effectiveness beyond business focused metrics: how to evaluate them, suitable classifiers;
- Creating forms of elicitation and enabling user control to improve the perception of the recommendations.
- EXPECTED PROPERTIES OF A RECOMMENDER SYSTEM
- Software architectures for usable recommender systems;
- Guidelines for building trust in recommendations;
- Solutions for enabling users and systems to work with large data;
- Representation of performance issues.