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 is directly affected by compositional phenomena inlanguage that act on the prior polarity of the words and phrases found in thetext. Negation is the most prevalent of these phenomena and in order tocorrectly predict sentiment, a classifier must be able to identify negation anddisentangle the effect that its scope has on the final polarity of a text. Thispaper proposes a multi-task approach to explicitly incorporate informationabout negation in sentiment analysis, which we show outperforms learningnegation implicitly in a data-driven manner. We describe our approach, acascading neural architecture with selective sharing of LSTM layers, and showthat explicitly training the model with negation as an auxiliary task helpsimprove the main task of sentiment analysis. The effect is demonstrated acrossseveral different standard English-language data sets for both tasks and weanalyze several aspects of our system related to its performance, varying typesand amounts of input data and different multi-task setups.

Improving Sentiment Analysis with Multi-task Learning of Negation