Icon

Medical Drug Sentiment Analysis using BERT Extension

NotesThe following workflow uses the BERT Extension in order to sentiment analysis on a drug sentiment dataset from Kaggle, Link: https://www.kaggle.com/arbazkhan971/analyticvidhyadatasetsentimentUsing 2 classes (positive, negative) will result in an accuracy of 82%. 3 classes (positive, negative, neutral) will result in an accuracy of 74%. Node 1Node 79Without fine tuningCheck Python dependenciesBERT modelcan be cached on diskWithout fine tuningNode 197Node 198Node 199 CSV Reader Partitioning BERT Predictor Conda EnvironmentPropagation BERT Model Selector BERT ClassificationLearner Scorer Row Filter Pre-Processing NotesThe following workflow uses the BERT Extension in order to sentiment analysis on a drug sentiment dataset from Kaggle, Link: https://www.kaggle.com/arbazkhan971/analyticvidhyadatasetsentimentUsing 2 classes (positive, negative) will result in an accuracy of 82%. 3 classes (positive, negative, neutral) will result in an accuracy of 74%. Node 1Node 79Without fine tuningCheck Python dependenciesBERT modelcan be cached on diskWithout fine tuningNode 197Node 198Node 199 CSV Reader Partitioning BERT Predictor Conda EnvironmentPropagation BERT Model Selector BERT ClassificationLearner Scorer Row Filter Pre-Processing

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: junhw
Created at: 2021-12-23
On NodePit since: 2021-12-30
Last update: 2024-12-17
Created with KNIME version: v4.5.0

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

Try NodePit Runner!