Special issue announcement: A special issue of ACM Transactions on Intelligent Systems and Technology on "Diversity and Discovery in Recommender Systems and Exploratory Search" has issued its call for papers. Submission deadline: 20 September 2012.

DiveRS 2011 – International Workshop on Novelty and Diversity in Recommender Systems

Most research and development efforts in the Recommender Systems field have been focused on accuracy in predicting and matching user interests. However there is a growing realization that there is more than accuracy to the practical effectiveness and added-value of recommendation. In particular, novelty and diversity have been identified as key dimensions of recommendation utility in real scenarios, and a fundamental research direction to keep making progress in the field.

Novelty is indeed essential to recommendation: in many, if not most scenarios, the whole point of recommendation is inherently linked to a notion of discovery, as recommendation makes most sense when it exposes the user to a relevant experience that she would not have found, or thought of by herself –obvious, however accurate recommendations are generally of little use.

Not only does a varied recommendation provide in itself for a richer user experience. Given the inherent uncertainty in user interest prediction –since it is based on implicit, incomplete evidence of interests, where the latter are moreover subject to change–, avoiding a too narrow array of choice is generally a good approach to enhance the chances that the user is pleased by at least some recommended item. Sales diversity may enhance businesses as well, leveraging revenues from market niches.

It is easy to increase novelty and diversity by giving up on accuracy; the challenge is to enhance these aspects while still achieving a fair match of the user's interests. The goal is thus generally to enhance the balance in this trade-off, rather than just a diversity or novelty increase.

DiveRS 2011 aims to gather researchers and practitioners interested in the role of novelty and diversity in recommender systems. The workshop seeks to advance towards a better understanding of what novelty and diversity are, how they can improve the effectiveness of recommendation methods and the utility of their outputs. We aim to identify open problems, relevant research directions, and opportunities for innovation in the recommendation business. The workshop seeks to stir further interest for these topics in the community, and stimulate the research and progress in this area.

Questions that the workshop aims to address include the following:

• What are the different notions and dimensions of novelty and diversity? Is it possible to establish a clear definition and/or taxonomy? How are novelty and diversity themselves different and related?
• How can diversity, novelty, and accuracy be enhanced together?
• What important differences arise between the end-user point of view and the system or the business perspective?
• How can novelty and diversity be measured and evaluated?
• What are the potential implications of novelty on user trust, and how can they be properly cared for?
• What are the differences and unexplored connections between diversity as researched in Recommender Systems and Information Retrieval?
• Is there a relevant relation between novelty, diversity and context in recommendation?
• To what extent are novelty and diversity procured by or missing from state of the art technologies?
• Do the different state of the art recommendation algorithms (content-based, kNN, matrix factorization, social, hybrid, ensembles, etc.) perform differently to each other in terms of novelty and diversity?
• To what extent are novelty and diversity a concern in the development of real-world recommender system applications, and how are they being addressed? What is the business value in novelty and diversity enhancement?
• What are the scenarios where novelty and diversity are most/least valuable or necessary? Are there situations in which novelty and diversity are not a desirable feature?

We welcome the participation of researchers, students, and practitioners in the Recommender Systems community and related areas such as Information Retrieval, Data Mining, Machine Learning, and Human-Computer Interaction, working in different application domains, working on or interested in the workshop topics.