Project

Opinion Detector

11 completions

~ 29 hours

3.6

Understand the basics of NLP and take a close look at one of its subfields — the sentiment analysis. Learn to preprocess and visualize data with the help of the NLTK and Matplotlib libraries. Detect a text sentiment using the lexicon-based approach and linear SVM classification with stochastic gradient descent optimization algorithms.

Provided by

JetBrains Academy

About

Sentiment analysis is, perhaps, the most popular application of NLP. It helps to extract opinions and determine what emotions a text expresses. We can use it almost anywhere, both for business and scientific research, to analyze social media feeds, movie or product reviews, emails, and so on. In this project, you'll write your sentiment analysis tool and experiment with the dataset that contains IMDB movie reviews.

Training project

This project allows you to practice and strengthen your coding skills, helping you get ready for more advanced tasks ahead.

What you'll learn

Once you choose a project, we'll provide you with a study plan that includes all the necessary topics from your course to get it built. Here’s what awaits you:

Load the text corpus of movie reviews.

Preprocess the corpus and save your results.

Implement the rule-based approach. Use positive and negative wordlists, count how many words you have in each review, and visualize your findings.

Detect the sentiment of a text with machine learning. Prepare your data by splitting it into test and training sets and vectorizing it.

Use the SVM classifier optimized with the stochastic gradient descent to predict the opinion of a review and compare the prediction results with the rule-based approach.

Reviews

synth

2 years ago

Moderator

4.3

I have learned about TfidfVectorizer, SGDClassifier, classification_report, train_test_split and how to use it to predict 'Positive'/'Negative' opinions.

ÇAĞRI KURT

4 years ago

4.0

It was very useful project for machine learning and data science as well as NLP.

3.6

Learners who completed this project within the course rated it as follows:

Usefulness

4.5

Fun

3.5

Clarity

2.8