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 and emotion detection are important research topics innatural language processing (NLP) and benefit many downstream tasks. With thewidespread application of LLMs, researchers have started exploring theapplication of LLMs based on instruction-tuning in the field of sentimentanalysis. However, these models only focus on single aspects of affectiveclassification tasks (e.g. sentimental polarity or categorical emotions), andoverlook the regression tasks (e.g. sentiment strength or emotion intensity),which leads to poor performance in downstream tasks. The main reason is thelack of comprehensive affective instruction tuning datasets and evaluationbenchmarks, which cover various affective classification and regression tasks.Moreover, although emotional information is useful for downstream tasks,existing downstream datasets lack high-quality and comprehensive affectiveannotations. In this paper, we propose EmoLLMs, the first series ofopen-sourced instruction-following LLMs for comprehensive affective analysisbased on fine-tuning various LLMs with instruction data, the first multi-taskaffective analysis instruction dataset (AAID) with 234K data samples based onvarious classification and regression tasks to support LLM instruction tuning,and a comprehensive affective evaluation benchmark (AEB) with 14 tasks fromvarious sources and domains to test the generalization ability of LLMs. Wepropose a series of EmoLLMs by fine-tuning LLMs with AAID to solve variousaffective instruction tasks. We compare our model with a variety of LLMs onAEB, where our models outperform all other open-sourced LLMs, and surpassChatGPT and GPT-4 in most tasks, which shows that the series of EmoLLMs achievethe ChatGPT-level and GPT-4-level generalization capabilities on affectiveanalysis tasks, and demonstrates our models can be used as affective annotationtools.

EmoLLMs: A Series of Emotional Large Language Models and Annotation Tools for Comprehensive Affective Analysis