The phenomenon often referred to as the “filter-bubble,” i.e., the effect that collaborative, as well as content-based recommender systems keep making obvious, uninspiring, and therefore disengaging suggestions based on previous interactions, has emphasized the value of system qualities beyond pure accuracy, e.g., diversity, novelty, serendipity, or unexpectedness, to keep the user satisfied. In fact, these approaches to kicking the user out of his or her “comfort zone” seem to be highly promising methods to increase satisfaction with a system in the long run. To go even one step further, we also want to explore concepts along three qualities we refer to as surprise, opposition, and obstruction. Surprise relates to existing concepts like serendipity in complex scenarios. Opposition, as an extreme form of variation, is highly subjective and context-dependent. Obstruction refers to the intentional restriction of functionality through the machine in an active manner by “embodying opposition”. We are interested in these aspects in the context of personalized and adaptive systems, such as recommender systems, user modeling, e.g., through personality-based preference models, and creative processes that are facilitated through collaborations with intelligent machines.
Topics of Interest
- Unexpectedness in retrieval and recommender systems
- Serendipity, diversity, and novelty
- User-centric evaluation studies on aspects of diversity and serendipity
- Approaches to content discovery
- Inspirational recommender systems
Aspects of personalization in inspirational systems
- User models facilitating imitation, subversion, and opposition in creative and cooperative systems
- Learning to variate
- Systems and user models promoting self-awareness and/or self-growth
- Anti-communal reinforcement
- Anti-confirmation bias
- Chance and randomness in intelligent systems
- Case studies of intelligent systems in creative domains, e.g., music creation
Important Dates and Format
Workshop paper submission deadline:
April 20, 2017 April 27, 2017 (extended)
Notification to authors: May 20, 2017
Camera-ready paper: May 28, 2017
The SOAP workshop will be held in a mini-conference style. Based on the recency of the above mentioned developments in recommender systems, music creation, and even computational creativity research, we consider this to be a breaking topic highly relevant to the UMAP community and beyond. We ask prospective participants to submit a paper detailing their position or technical contribution with regard to the questions discussed above prior to the workshop. To this end, we allow for different types of paper entries (non-anonymized):
- position paper (extended abstract, up to 4 pages)
- technical short paper (up to 4 pages)
- technical full paper (up to 6 pages)
Submissions are to be made through the SOAP submission website on EasyChair:
Submission ACM Standard (SIGCONF) templates: http://www.acm.org/publications/proceedings-template .
Submissions will be reviewed by at least three members of the program committee to select participants. Authors of accepted submissions will be required to give a short presentation at the workshop.
All accepted papers will be published by ACM as a joint volume of Extended UMAP 2017 Proceedings and will be available via the ACM Digital Library. At least one author of each accepted paper must register for the particular workshop and present the paper there. We encourage the authors to register for the whole conference.