Time-evolving Text Classification with Deep Neural Networks

Time-evolving Text Classification with Deep Neural Networks

Yu He, Jianxin Li, Yangqiu Song, Mutian He, Hao Peng

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Main track. Pages 2241-2247. https://doi.org/10.24963/ijcai.2018/310

Traditional text classification algorithms are based on the assumption that data are independent and identically distributed. However, in most non-stationary scenarios, data may change smoothly due to long-term evolution and short-term fluctuation, which raises new challenges to traditional methods. In this paper, we present the first attempt to explore evolutionary neural network models for time-evolving text classification. We first introduce a simple way to extend arbitrary neural networks to evolutionary learning by using a temporal smoothness framework, and then propose a diachronic propagation framework to incorporate the historical impact into currently learned features through diachronic connections. Experiments on real-world news data demonstrate that our approaches greatly and consistently outperform traditional neural network models in both accuracy and stability.
Keywords:
Machine Learning: Classification
Machine Learning: Data Mining
Machine Learning: Neural Networks
Natural Language Processing: Text Classification
Machine Learning Applications: Applications of Supervised Learning