Icon

00_​Topic_​Modeling_​with_​Verified_​Components

Topic Modeling with Verified Components

In this workflow you can see how these 4 components can be adopted in combination with the Topic Extractor (Parallel LDA) node.
Right click on the Topic Explorer Views to open the interactive views.

Read more on the component pages at knime.com/verified-components. References are also available below in this workflow page.

Interactive Views Scoring Training Interactive Views Predictor Documents Data Preparation Topic Modeling with Verified Components Four components are executed on different settings and modes. This should help with an overview of how these components can be adopted in different scenarios: - STM model or LDA model - scoring one or multiple models topics - visualizing default topic labels or automated/custom labels Note: make sure to open the views of the components in the blue annotations. k = 20add model idexplore LDA topicson train corpusexplore STM topicson holdout corpusexplore STM topicswith automated labelson train corpusexplore STM topicswith custom labelson train corpusscore multiple models on holdout corpusscore LDA on train corpusscore STM on holdout corpusoptimal K searchk = 20no metadatak = 20source + s(day)holdout predsGroupBy Topic Extractor(Parallel LDA) Partitioning ConstantValue Column Concatenate Table Editor Rename Topics witha Custom Label ConstantValue Column Row Sampling Topic Explorer View Topic Explorer View Topic Explorer View Topic Explorer View Topic Scorer (Labs) Topic Scorer (Labs) Topic Scorer (Labs) Topic Extractor(STM) Topic Extractor(STM) Topic Extractor(STM) Topic Assigner(STM) Read andPrepare Docs Interactive Views Scoring Training Interactive Views Predictor Documents Data Preparation Topic Modeling with Verified Components Four components are executed on different settings and modes. This should help with an overview of how these components can be adopted in different scenarios: - STM model or LDA model - scoring one or multiple models topics - visualizing default topic labels or automated/custom labels Note: make sure to open the views of the components in the blue annotations. k = 20add model idexplore LDA topicson train corpusexplore STM topicson holdout corpusexplore STM topicswith automated labelson train corpusexplore STM topicswith custom labelson train corpusscore multiple models on holdout corpusscore LDA on train corpusscore STM on holdout corpusoptimal K searchk = 20no metadatak = 20source + s(day)holdout predsGroupBy Topic Extractor(Parallel LDA) Partitioning ConstantValue Column Concatenate Table Editor Rename Topics witha Custom Label ConstantValue Column Row Sampling Topic Explorer View Topic Explorer View Topic Explorer View Topic Explorer View Topic Scorer (Labs) Topic Scorer (Labs) Topic Scorer (Labs) Topic Extractor(STM) Topic Extractor(STM) Topic Extractor(STM) Topic Assigner(STM) Read andPrepare Docs

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: Paolo Tamagnini
Created at: 2023-05-02
On NodePit since: 2023-07-06
Last update: 2024-04-27
Created with KNIME version: v4.7.4
Tags: stmstructural topic modelingtopicldasemantic coherencecoherenceexclusivityfrex

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

Try NodePit Runner!