Explaining Sentiment Classification

Marvin Rajwadi, Cornelius Glackin, Julie Wall, Gérard Chollet, Nigel Cannings

This paper presents a novel 1-D sentiment classifier trained on the benchmark IMDB dataset. The classifier is a 1-D convolutional neural network with repeated convolution and max pooling layers. The main contribution of this work is the demonstration of a deconvolution technique for 1-D convolutional neural networks that is agnostic to specific architecture types. This deconvolution technique enables text classification to be explained, a feature that is important for NLP-based decision support systems, as well as being an invaluable diagnostic tool.

 DOI: 10.21437/Interspeech.2019-2743

Cite as: Rajwadi, M., Glackin, C., Wall, J., Chollet, G., Cannings, N. (2019) Explaining Sentiment Classification. Proc. Interspeech 2019, 56-60, DOI: 10.21437/Interspeech.2019-2743.

  author={Marvin Rajwadi and Cornelius Glackin and Julie Wall and Gérard Chollet and Nigel Cannings},
  title={{Explaining Sentiment Classification}},
  booktitle={Proc. Interspeech 2019},