SOAP 2016 - Workshop on Surprise, Opposition, and Obstruction in Adaptive and Personalized Systems (SOAP)

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 addition to these, in this workshop, we want to explore concepts beyond these qualities, namely 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, such as music making, that are facilitated through collaborations with intelligent machines and their effect on creative output.
Topics of Interest
Surprise and unexpectedness in retrieval and recommender systems
Serendipity, diversity, and novelty
User-centric evaluation studies on aspects of diversity and serendipity
Inspirational recommender systems
Aspects of personalization in inspirational systems
Formal models of creativity
User models dealing with opposition and “otherness”
The roles of chance and randomness in intelligent and user-adaptive systems
Imitation, subversion, and opposition in creative and cooperative systems
Learning to variate
Models for obstruction in collaborative scenarios
Case studies of intelligent systems in creative domains, e.g., music creation
Automatic improvisation and variation systems
Intelligent accompaniment
Personalized sound quality verbalization and semantic embeddings
Sound retrieval for music creators