This Title All WIREs
How to cite this WIREs title:
WIREs Data Mining Knowl Discov
Impact Factor: 7.250

Stacked denoising autoencoders for sentiment analysis: a review

Full article on Wiley Online Library:   HTML PDF

Can't access this content? Tell your librarian.

Deep learning has been shown to outperform numerous conventional machine learning algorithms (e.g., support vector machines) in many fields, such as image processing and text analyses. This is due to its outstanding capability to model complex data distributions. However, as networks become deeper, there is an increased risk of overfitting and higher sensitivity to noise. Stacked denoising autoencoders (SDAs) provide an infrastructure to resolve these issues. In the field of sentiment recognition from textual contents, SDAs have been widely used (especially for domain adaptation), and have been consistently refined and improved through defining new alternate topologies as well as different learning algorithms. A wide selection of these approaches are reviewed and compared in this article. The results coming from the reviewed works indicate the promising capability of SDAs to perform sentiment recognition on a multitude of domains and languages. WIREs Data Mining Knowl Discov 2017, 7:e1212. doi: 10.1002/widm.1212 This article is categorized under: Algorithmic Development > Text Mining Technologies > Machine Learning
(a) Autoencoder, (b) denoising autoencoder, (c) SDA with domain and sentiment supervision (SDA‐DSS), (d) domain adversarial neural network (DANN) with ‘SDA representation’. d(.), domain; y(.), label.
[ Normal View | Magnified View ]
Comparative performance of domain adaptation on the Amazon Reviews dataset.
[ Normal View | Magnified View ]

Browse by Topic

Algorithmic Development > Text Mining
Technologies > Machine Learning

Access to this WIREs title is by subscription only.

Recommend to Your
Librarian Now!

The latest WIREs articles in your inbox

Sign Up for Article Alerts