The ACM Recommender Systems Conference (RecSys) is the premier international forum for the presentation of new research results, systems and techniques in the broad field of Recommender Systems.
Recommender System focuses on a particular form of information filtering, that exploits past behaviors and user similarities to generate a list of data points that is personally tailored to end-user’s preferences. For instance, Companies like Amazon, Netflix, LinkedIn, and Pandora leverage recommender systems to help users discover new and relevant items (products, videos, jobs, music), creating a delightful user experience while driving incremental revenue.
In order to move forward in this domain, more than 900 participants, from various fields of academia and industry presented their latest results in the area of new trends and challenges in Recommendation components in innovative application contexts.
Published papers went through a rigorous full peer review process and four of our experts from the Social Computing Team, namely, Elisabeth Lex (Head), Dominik Kowald (Post Doctorate), Emanuel Lacic and Tomislav Duricic (PHD Students) presented three extremely relevant and well received Papers.
The First Paper titled ‘Should we Embed? A Study on the Online Performance of Utilizing Embeddings for Real-Time Job Recommendations’ was an online study in the Studo Jobs Portal (Moshbit GmbH) that showed the value add of deep learning for recommending jobs.
The Second Paper titled ‘Evaluating Tag Recommendations for E-Book Annotation Using a Semantic Similarity Metric’ a joint project between the Know-Center and the Hanseatic Society for the Publishing industry, summarized the findings of how the combination of several data sources leads to a better Recommender System for the semi-automatic indexing of books.
The Third Paper titled, ‘Using the Open Meta Kaggle Dataset to Evaluate Tripartite Recommendations in Data Markets’ showed results from the recently completed Data Market Austria FFG flagship project. This was the first time that the so-called tripartite recommendation problem, i.e. the connection between users, data sets and services, was examined and initial evaluation results were shown.
We at Know-Center are proud participants of the ACM RecSys and are looking forward to more innovation and research in this area.
More about the Conference