ITEC RESEARCH SEMINAR

Prof. Verbert will talk about Interactive Recommender Systems:

Researchers have become more aware of the fact that effectiveness of recommender systems goes beyond recommendation accuracy. Thus, research on these human factors has gained increased interest, for instance by combining interactive visualization techniques with recommendation techniques to support transparency and controllability of the recommendation process. In this talk, I will present our work on interactive visualizations to enable end-users to interact with recommender systems. The objective is two-fold: 1) to explain the rationale of recommendations as a basis to increase user trust and acceptance of recommendations, and 2) to incorporate user feedback and input into the recommendation process and to help them steer this process. In addition, I will present the results of several user studies that investigate how such explanations and user control interact with different personal characteristics, such as expertise and visual working memory. I will also present concrete applications in the field of learning analytics and job recommender systems that use visualization techniques to support interaction  with recommender systems.

Alireza Gharahighehi, PHD researcher within the team of Prof. Celine Vens, will talk about Recommender systems: an introduction and the NewsButler project

Personalization and recommender systems can be applied to nearly every discipline. There are examples of recommender systems in e-commerce, advertising , news, education, health, social networks and so on. In this talk, first I will introduce some basic recommendation methods. Then, I will present the objectives of ongoing research project “NewsButler”. NewsButler is a news recommendation project where we work with data from Roularta Media Group. This project consists of three main phases: I) Recommending news topics, II) Recommending articles from news topics that the user follows and III) Recommending articles from news topics that the user does not (yet) follow. I will explain the proposed method and results of the first phase. The proposed method is an extended form of Bayesian Personalized Ranking (BPR) which is a learning to rank method based on implicit feedback.

  • Date: 24.05.2019
  • Venue: IICK 00.29 (remote participation possible
  • Time: 12-1.30 pm
Scroll to top