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 a key component in various text mining applications.Numerous sentiment classification techniques, including conventional and deeplearning-based methods, have been proposed in the literature. In most existingmethods, a high-quality training set is assumed to be given. Nevertheless,constructing a high-quality training set that consists of highly accuratelabels is challenging in real applications. This difficulty stems from the factthat text samples usually contain complex sentiment representations, and theirannotation is subjective. We address this challenge in this study by leveraginga new labeling strategy and utilizing a two-level long short-term memorynetwork to construct a sentiment classifier. Lexical cues are useful forsentiment analysis, and they have been utilized in conventional studies. Forexample, polar and privative words play important roles in sentiment analysis.A new encoding strategy, that is, $\rho$-hot encoding, is proposed to alleviatethe drawbacks of one-hot encoding and thus effectively incorporate usefullexical cues. We compile three Chinese data sets on the basis of our labelstrategy and proposed methodology. Experiments on the three data setsdemonstrate that the proposed method outperforms state-of-the-art algorithms.

$\rho$-hot Lexicon Embedding-based Two-level LSTM for Sentiment Analysis