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

While reaching for NLP systems that maximize accuracy, other importantmetrics of system performance are often overlooked. Prior models are easilyforgotten despite their possible suitability in settings where large computingresources are unavailable or relatively more costly. In this paper, we performa broad comparative evaluation of document-level sentiment analysis models witha focus on resource costs that are important for the feasibility of modeldeployment and general climate consciousness. Our experiments considerdifferent feature extraction techniques, the effect of ensembling,task-specific deep learning modeling, and domain-independent large languagemodels (LLMs). We find that while a fine-tuned LLM achieves the best accuracy,some alternate configurations provide huge (up to 24, 283 *) resource savingsfor a marginal (<1%) loss in accuracy. Furthermore, we find that for smallerdatasets, the differences in accuracy shrink while the difference in resourceconsumption grows further.

Efficient Sentiment Analysis: A Resource-Aware Evaluation of Feature Extraction Techniques, Ensembling, and Deep Learning Models