Description & Objectives
Over the past decade, recommendation algorithms for ratings prediction and item ranking have steadily matured. However, these state-of-the-art algorithms are typically applied in relatively straightforward scenarios.
In reality, recommendation is often a more complex problem: it is usually just a single step in the user’s more complex background need. These background needs can often place a variety of constraints on which recommendations are interesting to the user and when they are appropriate. Users may want combinations of multiple items, or recommendations on the sequence of consumption. Moreover, different users may want different information about items, so beyond ranking the system needs to decide which information best to display to each user.
However, relatively little research has been done on these complex recommendation scenarios. The ComplexRec 2019 workshop aims to address this by providing an interactive venue for discussing approaches to recommendation in complex scenarios that have no simple one-size-fits-all solution. We are especially interested in papers that have a clear focus on complex user needs and tasks and the consequences for modelling the recommendation process, designing practical recommender systems and their evaluation in the covered domain(s). It is the follow-up to the successful ComplexRec workshops at RecSys 2017 and 2018.
Topics of interest
We invite original contributions about recommendation in complex scenarios. Topics of interest include, but are not limited to, the following:
- Task-based recommendation — Approaches that take the user’s background tasks and needs into account when generating recommendations
- Interactive recommendation — Techniques for successfully capturing, weighting, and integrating continuous user feedback into recommender systems, both in situations of sparse and rich user interaction
- Feature-driven recommendation — Techniques for eliciting, capturing and integrating rich information about user preferences for specific product features
- Constraint-based recommendation — Approaches that successfully combine state-of-the-art recommendation algorithms with complex knowledge-based or constraint-based optimization
- Query-driven recommendation — Techniques for eliciting and incorporating rich information about the user’s recommendation need (e.g., need for accessibility, engagement, socio-cultural values, familiarity, etc.) in addition to the standard user preference information
- Context-aware recommendation — Methods for the extraction and integration of complex contextual signals for recommendation
- Complex data sources — Approaches to dealing with complex data sources and how to infer user preferences from these sources
- Evaluation & validation — Approaches to the evaluation and validation of recommendation in complex scenarios
We encourage authors to submit short papers and position papers of 4-6 pages in length dedicated to any aspect of recommendation in complex scenarios.
Accepted submissions will then be invited for short presentations. Evaluation criteria for acceptance will include novelty, diversity, significance for theory/practice, quality of presentation, and the potential for sparking interesting discussion at the workshop. All submitted papers will be reviewed by the Program Committee. At least one author of each accepted paper must attend the workshop.
All submissions should be in English and should not have been published or submitted for publication elsewhere. Papers should be formatted in the ACM Proceedings Style and submitted via EasyChair (https://easychair.org/conferences/?conf=complexrec2019). Submissions will be published in the workshop proceedings.