M
Michael Jugovac
Researcher at Technical University of Dortmund
Publications - 20
Citations - 1152
Michael Jugovac is an academic researcher from Technical University of Dortmund. The author has contributed to research in topics: Recommender system & User interface. The author has an hindex of 12, co-authored 20 publications receiving 704 citations.
Papers
More filters
Journal ArticleDOI
News recommender systems – Survey and roads ahead
TL;DR: This work reviews the state-of-the-art of designing and evaluating news recommender systems over the last ten years and analyzes which particular challenges of news recommendation have been well explored and which areas still require more work.
Journal ArticleDOI
What recommenders recommend: an analysis of recommendation biases and possible countermeasures
TL;DR: It is shown that popular recommendation techniques—despite often being similar when compared with the help of accuracy measures—can be quite different with respect to which items they recommend.
Journal ArticleDOI
Interacting with Recommenders—Overview and Research Directions
Michael Jugovac,Dietmar Jannach +1 more
TL;DR: This work provides a comprehensive overview on the existing literature on user interaction aspects in recommender systems, covering existing approaches for preference elicitation and result presentation, as well as proposals that consider recommendation as an interactive process.
Journal ArticleDOI
Measuring the Business Value of Recommender Systems
Dietmar Jannach,Michael Jugovac +1 more
TL;DR: In this paper, the authors review existing publications on field tests of recommender systems and report which business-related performance measures were used in such real-world deployments and summarize common challenges of measuring the business value in practice and critically discuss the value of algorithmic improvements and offline experiments as commonly done in academic environments.
Proceedings ArticleDOI
Adaptation and Evaluation of Recommendations for Short-term Shopping Goals
TL;DR: The results indicate that maintaining short-term content-based and recency-based profiles of the visitors can lead to significant accuracy increases and show that the choice of the algorithm for learning the long-term preferences is particularly important at the beginning of new shopping sessions.