Hasso-Plattner-Institut
Prof. Dr. Felix Naumann
 

17.03.2020

Accepted Paper at ICWSM 2020

We are excited to announce that our paper "Top Comment or Flop Comment? Predicting and Explaining User Engagement in Online News Discussions" has been accepted as a full paper at the International AAAI Conference on Web and Social Media (ICWSM 2020). A pre-print of our paper can be downloaded here. The conference is scheduled to be held in Atlanta, Georgia, USA in June 2020. This year, 195 papers were submitted out of which 33 were accepted (17%).

Top Comment or Flop Comment? Predicting and Explaining User Engagement in Online News Discussions

Authors
Julian Risch, Ralf Krestel

Abstract

Comment sections below online news articles enjoy growing popularity among readers. However, the overwhelming number of comments makes it infeasible for the average news consumer to read all of them and hinders engaging discussions. Most platforms display comments in chronological order, which neglects that some of them are more relevant to users and are better conversation starters.

In this paper, we systematically analyze user engagement in the form of the upvotes and replies that a comment receives. Based on comment texts, we train a model to distinguish comments that have either a high or low chance of receiving many upvotes and replies. Our evaluation on user comments from TheGuardian.com compares recurrent and convolutional neural network models, and a traditional feature-based classifier. Further, we investigate what makes some comments more engaging than others. To this end, we identify engagement triggers and arrange them in a taxonomy. Explanation methods for neural networks reveal which input words have the strongest influence on our model's predictions. In addition, we evaluate on a dataset of product reviews, which exhibit similar properties as user comments, such as featuring upvotes for helpfulness.

Acknowledgments

We would like to thank Johannes Filter, Cornelius Hagmeister and Thomas Kellermeier for their contribution to this project during our seminar Text Mining in Practice in summer 2018.