Optimization of Topic Models using Grid Search Method

3.8
stars
12 ratings
Offered By
Coursera Project Network
In this Guided Project, you will:

Necessity for optimization of Topic Models

Grid Search Method for optimizing Topic Models

Evaluate a best fit model - Compare model parameters and goodness of model scores from basic model

Clock2 Hours
AdvancedAdvanced
CloudNo download needed
VideoSplit-screen video
Comment DotsEnglish
LaptopDesktop only

In this 2-hour long project-based course, you will learn how to optimize a topic model to achieve best fit using Grid Search method. Topic modelling is an efficient unsupervised machine learning tool that aids in analyzing the latent themes from text datasets. But it is also necessary to learn to optimize the models to obtain the best fit model in order to achieve better interpretable themes to gain meaningful insights. In this project you will learn about the statistical parameters to gauge the model quality and create interactive visualization of the themes for a more intuitive evaluation of topic models. The focus of this project is primarily from an application point of view instead of underlying statistical mechanisms. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

Skills you will develop

Topic Modelmodel optimizationHyperparameter OptimizationApplied Machine Learning

Learn step-by-step

In a video that plays in a split-screen with your work area, your instructor will walk you through these steps:

  1. Introduction

  2. Clean dataset & Visualize frequent words

  3. Tokenization, Lemmatization and Word Document Matrix

  4. Build LDA Model with Scikit Learn

  5. Grid Search for Model Optimization

  6. Visualization of Top N-words of Best Model

How Guided Projects work

Your workspace is a cloud desktop right in your browser, no download required

In a split-screen video, your instructor guides you step-by-step

Frequently asked questions

Frequently Asked Questions

More questions? Visit the Learner Help Center.