What are the current approaches for analyzing emotions within a piece of text? Which tools and Python packages should you use for sentiment analysis? This week, Jodie Burchell, developer advocate for data science at JetBrains, returns to the show to discuss modern sentiment analysis in Python.
Jodie holds a PhD in clinical psychology. We discuss how her interest in studying emotions has continued throughout her career.
In this episode, Jodie covers three ways to approach sentiment analysis. We start by discussing traditional lexicon-based and machine-learning approaches. Then, we dive into how specific types of LLMs can be used for the task. We also share multiple resources so you can continue to explore sentiment analysis on your own.
This week’s episode is brought to you by Sentry.
Course Spotlight: Learn Text Classification With Python and Keras
In this course, you’ll learn about Python text classification with Keras, working your way from a bag-of-words model with logistic regression to more advanced methods, such as convolutional neural networks. You’ll see how you can use pretrained word embeddings, and you’ll squeeze more performance out of your model through hyperparameter optimization.
00:00:00 – Introduction
00:02:31 – Conference talks in 2024
00:04:23 – Background on sentiment analysis and studying feelings
00:07:09 – What led you to study emotions?
00:08:57 – Dimensional emotion classification
00:10:42 – Different types of sentiment analysis
00:14:28 – Lexicon-based approaches
00:17:50 – VADER - Valence Aware Dictionary and sEntiment Reasoner
00:19:41 – TextBlob and subjectivity scoring
00:21:48 – Sponsor: Sentry
00:22:52 – Measuring sentiment of New Year’s resolutions
00:27:28 – Lexicon-based approaches links for experimenting
00:28:35 – Multiple language support in lexicon-based packages
00:35:23 – Machine learning techniques
00:39:20 – Tools for this approach
00:42:54 – Video Course Spotlight
00:44:15 – Advantages to the machine learning models approach
00:45:55 – Large language model approach
00:48:44 – Encoder vs decoder models
00:52:09 – Comparing the concept of fine-tuning
00:56:49 – Is this a recent development?
00:58:08 – Ways to practice with these techniques
01:00:10 – Do you find this to be a promising approach?
01:07:45 – Resources to practice with all the techniques
01:11:06 – Upcoming conference talks
01:11:56 – Thanks and goodbye