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

Anticipating audience reaction towards a certain text is integral to severalfacets of society ranging from politics, research, and commercial industries.Sentiment analysis (SA) is a useful natural language processing (NLP) techniquethat utilizes lexical/statistical and deep learning methods to determinewhether different-sized texts exhibit positive, negative, or neutral emotions.Recurrent networks are widely used in machine-learning communities for problemswith sequential data. However, a drawback of models based on Long-Short TermMemory networks and Gated Recurrent Units is the significantly high number ofparameters, and thus, such models are computationally expensive. This drawbackis even more significant when the available data are limited. Also, such modelsrequire significant over-parameterization and regularization to achieve optimalperformance. Tensorized models represent a potential solution. In this paper,we classify the sentiment of some social media posts. We compare traditionalrecurrent models with their tensorized version, and we show that with thetensorized models, we reach comparable performances with respect to thetraditional models while using fewer resources for the training.

Reducing Computational Costs in Sentiment Analysis: Tensorized Recurrent Networks vs. Recurrent Networks