Icon

Zero-shot text classification and evaluation for Sentiment Analysis in Spanish

This workflow shows how to use Symanto Brain for zero-shot text classification for the task of sentiment classification.

Zero shot classification on the Spanish SAB sentiment dataset (Navas-Loroetal., 2017)This workflow shows how to use the Symanto Brain for zero shot text classification, in this case for the task of sentiment classification.References María Navas-Loro, Víctor Rodríguez-Doncel, Idafen Santana-Perez, and Alberto Sánchez. 2017. Spanish corpus for sentiment analysis towards brands. In Speech andComputer, pages 680–689. Dataset freely available under the CC-BY 4.0 license. Load and preprocess dataset Dataset statistics Shows the statistical properties of thedataset. Zero-shot classification with Symanto BrainPlease note that the zero-shot task parameters (labels, language,etc.) and the authentication key must be introduced inside the Zero-shot component. Specifically at the Authentication and Zero-shotcomponents, respectively. Evaluate the modelCompute a confusion matrix betweenreal and predicted class values andcalculate the related metrics. Node 9sabNode 513Node 514Node 518 DuplicateRow Filter CSV Reader Dataset statisticscomponent Scorer Column Appender Zero-shot component ROC Curve Zero shot classification on the Spanish SAB sentiment dataset (Navas-Loroetal., 2017)This workflow shows how to use the Symanto Brain for zero shot text classification, in this case for the task of sentiment classification.References María Navas-Loro, Víctor Rodríguez-Doncel, Idafen Santana-Perez, and Alberto Sánchez. 2017. Spanish corpus for sentiment analysis towards brands. In Speech andComputer, pages 680–689. Dataset freely available under the CC-BY 4.0 license. Load and preprocess dataset Dataset statistics Shows the statistical properties of thedataset. Zero-shot classification with Symanto BrainPlease note that the zero-shot task parameters (labels, language,etc.) and the authentication key must be introduced inside the Zero-shot component. Specifically at the Authentication and Zero-shotcomponents, respectively. Evaluate the modelCompute a confusion matrix betweenreal and predicted class values andcalculate the related metrics. Node 9sabNode 513Node 514Node 518 DuplicateRow Filter CSV Reader Dataset statisticscomponent Scorer Column Appender Zero-shot component ROC Curve

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: mchinea
Created at: 2023-02-17
On NodePit since: 2023-04-27
Last update: 2024-12-21
Created with KNIME version: v4.7.0
Tags: Sentiment analysisText classificationMachine learningText processingNLPSentimentDeep learningSymanto

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!