Interactive intelligent systems use Artificial Intelligence technologies (e.g., from natural language processing) for building so-called intelligent systems with which people can interact to enhance or extend machine's capabilities (e.g., classifying images manually).
This semester we will deal with the topic "Interactive Recommender Systems". Interactive Recommender Systems extend the traditional approach of Recommender Systems in the field of Human-Computer Interaction with the realization of a dialogical interaction in which textual or visual explanations are given to the system-generated recommendations. The interaction with or the adaptation of the given recommendations take place through feedback to initiate such "dialogue". Explanations are generated, and feedback is stored using a user model for which different approaches (e.g., feature-based models) exist. Interactive Recommender Systems enable a better understanding of the relationship between the input of the system, i.e., the individual preferences and the recommendations given, allowing people to interact predictably and effectively.
In this proseminar, you will get an introduction to the topic Recommender Systems, with an emphasis on the interaction perspective, to contextualize these Intelligent Systems in the field of human-computer interaction. First, an introduction to Recommender Systems will be given. Building on this, we will open up existing approaches, methods, and implementations in the form of presentations. Each participant is expected to independently prepare, present, and discuss their presentation with the class. Based on the results of the discussion, a written summary elaboration needs to be carried out.
Jugovac, M., & Jannach, D. (2017). Interacting with Recommenders—Overview and Research Directions. ACM Transactions on Interactive Intelligent Systems (TiiS), 7(3), 10–46. http://doi.org/10.1145/3001837
He, C., Parra, D., & Verbert, K. (2016). Interactive recommender systems: A survey of the state of the art and future research challenges and opportunities. Expert Systems with Applications, 56, 9–27. http://doi.org/10.1016/j.eswa.2016.02.013