[kdd] Last CFP: ACM TIST Special Issue on Diversity and Discovery in Recommender Systems and Exploratory Search

[Pablo Castells]

--------------------------- Call for Papers ---------------------------
   ACM Transactions on Intelligent Systems and Technology (ACM TIST)
                            Special Issue on
 Diversity and Discovery in Recommender Systems and Exploratory Search
              http://tist.acm.org/CFPs/TIST-SI-DIVERS.pdf
-----------------------------------------------------------------------

* Submission deadline: 20 September 2012 *

Overview
--------

Most research and development efforts in information access technologies
have been focused on the accuracy in predicting and matching user
information needs. Moreover, accuracy has been defined as a property that
considers individual delivered items in isolation, or even more narrowly,
as the ability to reduce the errors between predicted user preference
values and explicit user votes. However there is a growing realization that
there is more than accuracy to the practical effectiveness and added-value
of delivered information. In particular, diversity and discovery have been
identified as key dimensions of information utility in real scenarios, and
a fundamental research direction to keep making progress in the field. The
importance of novelty anddiversity is particularly manifest in scenarios
such as automatic recommendation and exploratory search, in which user
needs involve some degree of uncertainty and/or underspecification, leaving
room for the system's initiative to complete and predict these needs on
behalf of –or in collaboration with– the user.

The intelligence to discover something novel is indeed essential to a
recommender system: in many, if not most scenarios, the whole point of
recommendation is inherently linked to the provision 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 past 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.

The value of diversity has likewise been acknowledged in exploratory
retrieval scenarios where information needs have a specific orientation,
but involve a degree of flexibility, generality and open-endedness
comparable to user needs in recommendation tasks. Discovery is indeed a
fundamental drive –and an inherent part of user goals– in informational and
exploratory search, where new theories and methods are being developed that
model novelty and relevance as two sides of the same coin.

Diversity and discovery represent a cutting-edge research area in
intelligent information access and delivery, eliciting increasing attention
from researchers and practitioners in the recommender systems, information
retrieval, and machine learning communities. This special issue seeks to
gather a selection of papers reporting leading research on diversity and
discovery perspectives in recommender systems and exploratory search,
providing a view of the latest advances in this scope.

Topics of interest
------------------

We invite the submission of high-quality manuscripts reporting relevant
research in the area of diversity, discovery, and novelty in recommender
systems and exploratory search. The special issue welcomes submissions
presenting theoretical, technical, experimental, methodological and/or
applicative contributions in this scope, addressing –though not limited to–
the following topics:

* Diversity and discovery modeling in recommender systems
  - Theoretical foundation for novelty and diversity
  - Recommendation novelty and diversity models
  - Popularity, risk, unexpectedness, surprisal, serendipity, freshness
  - Link to diversity models in Information Retrieval
* Diversity and discovery enhancement in recommender systems
  - Diversification methods
  - Recommendation of long-tail and difficult items, cold-start problem
  - Individual vs. global diversity
  - Machine Learning for diversity and discovery
* Diversity and discovery across recommendations
  - Diversity and discovery in sequential recommendation
  - Diversity and discovery in interactive recommendation
  - Aggregate diversity
  - Diversity and discovery in time and context
  - Novelty and trust
* Diversity and discovery in exploratory search
  - Novelty and diversity in informational search and exploratory browsing
  - Diversity and discovery in interactive search
  - Novelty, diversity and personalization
  - Novelty, learning and knowledge gain
* Diversity and discovery evaluation
  - Experimental methodologies and design
  - Novelty and diversity metrics
  - Datasets
  - User studies
* Applications
  - Discovery-oriented domains, applications, and scenarios
  - Business perspective on diversity and discovery
  - Domain-specific studies

Submissions
-----------

Manuscripts shall be sent through the ACM TIST electronic submission system
at http://mc.manuscriptcentral.com/tist (please select "Special Issue:
Diversity and Discovery in Recommender Systems and Exploratory Search" as
the manuscript type). Submissions shall adhere to the ACM TIST instructions
and guidelines for authors available at the journal web site:
http://tist.acm.org.

Each paper will be evaluated by at least two reviewers. The papers will be
evaluated for their originality, contribution significance, soundness,
clarity, and overall quality. The interest of contributions will be
assessed in terms of technical and scientific findings, contribution to the
knowledge and understanding of the problem, methodological advancements,
and/or applicative value.

Important Dates
---------------

- Deadline for submission: 20 September 2012
- Review notification: 15 November 2012
- Revised manuscript due: 20 December 2012

Guest Editors
-------------

Pablo Castells, Universidad Autonoma de Madrid
Jun Wang, University College London
Ruben Lara, Telefonica, Investigacion y Desarrollo
Dell Zhang, Birkbeck, University of London
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.ivoa.net/pipermail/kdd/attachments/20120827/93a30e87/attachment-0001.html>