Speaker:: Sebastian Cattes
Track: PyData: Natural Language Processing Can we predict a reader's engagement time before publishing an article?
This talk presents a use case performed together with a regional German newspaper that analyses to what extent user engagement can be understood and predicted based on an article's texts and metadata.
A combination of advanced statistical and NLP deep learning models (BERT) was trained on a corpus of articles to model online reading behavior.
The talk focuses on the applied methods and shows Explainable AI techniques to get a microscopic understanding of driving mechanisms of user engagement.
Recorded at the PyConDE & PyData Berlin 2022 conference, April 11-13 2022. https://2022.pycon.de More details at the conference page: https://2022.pycon.de/program/XQMVKN Twitter: https://twitter.com/pydataberlin Twitter: https://twitter.com/pyconde