FewCLUE: EPRSTMT (E-commerce Sentiment Analysis)

FewCLUE's sentiment task: classify a Chinese e-commerce product review as positive or negative, learned from 32 labelled training reviews.

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categoryreasoning
Subcategorybinary sentiment classification of e-commerce product reviews, few-shot
Page statusunknown
Metricaccuracy
Directionhigher_is_better
Unit%
Dataset size610
PublisherCLUE team

What it measures

A short Chinese e-commerce product review; the model classifies its sentiment as Positive or Negative, learned few-shot from 32 labelled training reviews.

Task format

Binary sentiment classification, graded on the single correct label; evaluated from a 32-example few-shot training split, one of five parallel splits FewCLUE provides for this task.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub