Sebastian Cattes: Performing Content: Can NLP and Deep Learning algorithms predict reader prefere...

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. More details at the conference page: Twitter: Twitter: