Neural opinion dynamics model for the prediction of user-level stance dynamics
作者：
Highlights：
• A novel neural dynamic model for the prediction of user-level stance dynamics.
• Neighbors’ topic-associated impacts are modelled by an attention mechanism.
• User’s posting behaviors are simulated by a Recurrent Neural Network.
• The model’s parameters are continuously updated with the stream data.
• Experiments against static and dynamic alternatives show the effectiveness.
摘要
•A novel neural dynamic model for the prediction of user-level stance dynamics.•Neighbors’ topic-associated impacts are modelled by an attention mechanism.•User’s posting behaviors are simulated by a Recurrent Neural Network.•The model’s parameters are continuously updated with the stream data.•Experiments against static and dynamic alternatives show the effectiveness.
论文关键词：Natural language processing,Opinion mining,Social networks,Dynamic modelling
论文评审过程：Received 15 October 2018, Revised 23 March 2019, Accepted 26 March 2019, Available online 29 March 2019, Version of Record 13 January 2020.
论文官网地址：https://doi.org/10.1016/j.ipm.2019.03.010
