Adaptive Window Strategy for Topic Modeling in Document Streams

Article Number
8489771
Citation
2018 International Joint Conference on Neural Networks (IJCNN 2018)
Contribution to Conference
2018 International Joint Conference on Neural Networks, IJCNN 2018  
Publisher DOI
10.1109/IJCNN.2018.8489771
Scopus ID
2-s2.0-85056490837
Extracting global themes from a written text has recently become a major issue for computational intelligence, in particular in Natural Language Processing communities. Among all proposed solutions, Latent Dirichlet Allocation (LDA) has gained a vast interest and several variants have been proposed to adapt to changing environments. With the emergence of data streams, for instance from social media, the domain faces a new challenge: Topic extraction in real time. In this paper, we propose a simple approach called Adaptive Window based Incremental LDA (AWILDA) originating from the cross-over between LDA and state-of-the-art methods in data stream mining. We train new topic models only when a drift is detected and select training data on the fly using ADWIN algorithm. We provide both theoretical guarantees for our method and experimental validation on artificial and real-world data.