Spending an uncontrolled quantity and quality of time on digital information sites is affecting our well-being and can lead to serious problems in the long term. In this paper, we present a sequential recommendation framework that uses deep reinforcement learning to capture the users' short and long-term interests, with a proposed use case of blending social news with recommended micro-learning informative news items that can help users derive useful outcomes out of their presence online.
Einzelheiten
Titel
A user centered news recommendation system
Autor(en)/ in(nen)
Islambouli, Rania (EPFL, Lausanne, Switzerland) Ingram, Sandy (School of Engineering and Architecture (HEIA-FR), HES-SO University of Applied Sciences Western Switzerland) Gillet, Denis (EPFL, Lausanne, Switzerland)
Datum
2021-10
Veröffentlich in
Proceedings of 4th Workshop on Human Factors in Hypertext, 30 July- 3 August, 2021, Virtual Event, Ireland
Band
2021, pp. 15-16
Verlag
Virtual Event, Ireland, 30 July -3 August 2021
Umfang
2 p.
Vorgestellt auf
4th Workshop on Human Factors in Hypertext, Virtual Event, Ireland, 2021-07-30, 2021-08-03