English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Sentiment analysis has been widely used by businesses for social mediaopinion mining, especially in the financial services industry, where customers'feedbacks are critical for companies. Recent progress of neural network modelshas achieved remarkable performance on sentiment classification, while the lackof classification interpretation may raise the trustworthy and many otherissues in practice. In this work, we study the problem of improving theexplainability of existing sentiment classifiers. We propose two dataaugmentation methods that create additional training examples to help improvemodel explainability: one method with a predefined sentiment word list asexternal knowledge and the other with adversarial examples. We test theproposed methods on both CNN and RNN classifiers with three benchmark sentimentdatasets. The model explainability is assessed by both human evaluators and asimple automatic evaluation measurement. Experiments show the proposed dataaugmentation methods significantly improve the explainability of both neuralclassifiers.

Improving the Explainability of Neural Sentiment Classifiers via Data Augmentation