Julian Risch, Victor Künstler, Ralf Krestel
We are excited to announce that our full paper "HyCoNN: Hybrid Cooperative Neural Networks for Personalized News Discussion Recommendation" by Julian Risch, Victor Künstler and Ralf Krestel has been accepted for publication at the International Joint Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT 2020). The paper is based on the master's thesis by Victor Künstler. A preprint can be accessed here and the code is available on GitHub. A video presentation is on YouTube.
Many online news platforms provide comment sections for reader discussions below articles. While users of these platforms often read comments, only a minority of them regularly write comments. To encourage and foster more frequent engagement, we study the task of personalized recommendation of reader discussions to users. We present a neural network model that jointly learns embeddings for users and comments encoding general properties. Based on explicit and implicit user feedback, we sample relevant and irrelevant reader discussions to build a representative training dataset. We compare to several baselines and state-of-the-art approaches in an evaluation on two datasets from The Guardian and Daily Mail. Experimental results show that the recommendations of our approach are superior in terms of precision and recall. Further, the learned user embeddings are of general applicability because they preserve the similarity of users who share interests in similar topics.