Expliquewatch · explain · prove

← all topics

Building a sentiment analysis pipeline with huggingface

8 lessons · 47:14 · updated 9/9/2026

Watch them in order, then explain the topic in your own words below.

Nobody with subject knowledge has checked this course yet. It was put together automatically.

What you will do in this course

  • What is Hugging Face
  • Models and tokenizers
  • Fine-tune on your data
  • Sentiment with pipeline()
  • Classify text with PyTorch
  • Save and load models
  • Pick models from the Hub
  • Compare sentiment model results
0 / 8 lessons watched

Getting started

2 lessons · short section, not a full path on its own

1. What is Hugging Face?

Hugging Face · watch the original · 0:45

2. Pipeline

Sentiment with pipeline()

Patrick Loeber · watch the original · 8:36

Now you explain it

Close what you watched and explain the topic in your own words in 30 seconds. What you can explain is what you have learned. You are marked against this course's lessons and nothing beyond them.

Explain how you would do this: Getting started — Sentiment with pipeline().

You are judged on these, and nothing else in the course:

  • What is Hugging Face
  • Sentiment with pipeline()

Doing it properly

4 lessons

1. Model And Tokenizer

Models and tokenizers

Patrick Loeber · watch the original · 6:01

2. PyTorch classification

Classify text with PyTorch

Patrick Loeber · watch the original · 6:35

3. Model Hub

Pick models from the Hub

Patrick Loeber · watch the original · 7:57

4. Compare Results

Compare sentiment model results

Rob Mulla · watch the original · 9:00

Now you explain it

Close what you watched and explain the topic in your own words in 30 seconds. What you can explain is what you have learned. You are marked against this course's lessons and nothing beyond them.

Explain how you would do this: Doing it properly — Pick models from the Hub.

You are judged on these, and nothing else in the course:

  • Models and tokenizers
  • Classify text with PyTorch
  • Pick models from the Hub

Going deeper

2 lessons · short section, not a full path on its own

1. Fine Tuning

Fine-tune on your data

Patrick Loeber · watch the original · 6:42

2. Saving And Loading

Save and load models

Patrick Loeber · watch the original · 1:38

Now you explain it

Close what you watched and explain the topic in your own words in 30 seconds. What you can explain is what you have learned. You are marked against this course's lessons and nothing beyond them.

Explain how you would do this: Going deeper — Save and load models.

You are judged on these, and nothing else in the course:

  • Fine-tune on your data
  • Save and load models

Not part of the path

Added by readers, or indexed before this course was sorted. These are not counted as one of the three sections.

1. C16 YouTube comments sentiment Analysis using Machine Learning

CSM CMRTC · watch the original · 1:03

2. huggingface sentiment analysis model using transformers | machine learning

CodewithAI · watch the original · 0:47

3. Hugging Face Tutorial — Full Extracted Content

The ThinkLab by Saurabh · watch the original · 0:06 · a taster

4. Sentiment analysis

KgBase · watch the original · 0:41

5. Zero Shot Learning - Demo of Huggingface Transformers

Torsten Volk · watch the original · 1:30

6. Hugging Face: Run a Real AI Model in ONE Line of Code

Command Line · watch the original · 0:54

7. How to set up and use the HuggingFace Transformers library

AssemblyAI · watch the original · 0:57

8. Natural language processing text summarization with transformers ( hugging face)

TotemX Dev · watch the original · 1:04

9. Automatic Speech Recognition in 4 Lines of Python code with HuggingFace

AssemblyAI · watch the original · 0:48

10. Build AI Apps with Hugging Face in 5 Lines of Code

CodeVisium · watch the original · 0:10 · a taster

11. sentiment Analysis using BERT

Odela Pradeep · watch the original · 0:45

12. Setup + NLTK

Rob Mulla · watch the original · 9:34

Turn what you built into work

  1. Find a business with a task it repeats by hand: answering the same messages, copying orders into a spreadsheet, booking by phone.
  2. Adapt what you built in this course to that task and show it working. Your task's proof is your demo.
  3. Do the first setup for a small fee or free, and ask for a review that describes the result in return.

A suggestion, not a promise of earnings.