Learn how to perform sentiment analysis and emotion detection using TextBlob, NLTK, BERT, VADER, NRCLex, MultinomialNB
What you'll learn
Learn how to perform sentiment analysis on customer review data using TextBlob
Learn how to analyze emotional aspect of customer reviews using EmoLex
Learn how to perform sentiment analysis on twitter post data using VADER
Learn how to analyze emotional aspect of tweets using NRCLex
Learn how to predict sentiment of a tweet using BERT
Learn how to predict sentiment of a tweet using Multinomial Naive Bayes
Learn how to identify keywords that are frequently used in positive and negative customer reviews
Learn how to find correlation between customer ratings and sentiment
Case study: applying sentiment analysis on customer review dataset and predict if a review is more likely to be positive, negative or neutral
Learn factors that contribute to bias in customer reviews
Learn how to clean dataset by removing missing rows and duplicate values
Learn the basic fundamentals of sentiment analysis and its practical applications
Requirements
No previous experience in sentiment analysis is required
Basic knowledge in Python and NLP
Description
Welcome to Performing Sentiment Analysis on Customer Reviews & Tweets course. This is a comprehensive project based course where you will learn step by step on how to conduct sentiment analysis and emotional detection on customer review and twitter post datasets using TextBlob, Natural Language Toolkit, and BERT models. This course is a perfect combination between theory and hands-on application, providing you with practical skills to extract valuable insights from textual data. This course will be mainly focusing on two major objectives, the first one is data analysis where you will explore the customer review and twitter post datasets from multiple perspectives, meanwhile the second objective is sentiment analysis where you will learn to detect emotions and bias from customer reviews and twitter posts. In the introduction session, you will learn the basic fundamentals of sentiment analysis, such as getting to know its practical applications and models that will be used in our projects. Then, in the next session, we are going to have a case study where you will learn how sentiment analysis actually works. We are going to use customer reviews dataset to perform feature extraction and make predictions if a review is more likely to be positive, negative, or neutral. Afterward, you will also learn about several factors that contribute to bias in customer reviews, for examples like algorithmic amplification, emotional bias, and financial incentives. After learning all necessary knowledge about sentiment analysis, we will begin the project. Firstly you will be guided step by step on how to set up Google Colab IDE. In addition to that, you will also learn how to find and download customer reviews and twitter post dataset from Kaggle. Once everything is all set, we will enter the main section of the course which is the project section. The project will consist of two main parts, in the first part, you will learn step by step on how to perform sentiment analysis on customer reviews dataset, you will extensively learn how to make accurate predictions whether the review indicates customer's satisfaction or dissatisfaction based on the training data. Meanwhile, in the second part you will be guided step by step on how to perform sentiment analysis on twitter posts dataset, specifically you will analyse the emotional aspect of the tweets using Natural Language Toolkit.First of all, before getting into the course, we need to ask ourselves this question: why should we learn sentiment analysis? Well, there are many reasons why, but here is my answer, with the rise of E-commerce and businesses starting to expand their market online, as a result, more and more customers are starting to purchase products online and after purchasing the product, most likely they will also leave reviews telling their opinions about the product. In addition to that, sometimes they also have meaningful discussions about a specific product on social media. However, not a lot of people realize that those customer reviews and social media posts can potentially be transformed into valuable insights for the business, for instance, by evaluating the complaints from the customers in the review section, the company will be able to make better business decisions and improve the quality of their products based on their customer suggestions.Below are things that you can expect to learn from this course:Learn the basic fundamentals of sentiment analysis and its practical applicationsCase study: applying sentiment analysis on customer review dataset and predict if a review is more likely to be positive, negative or neutralLearn factors that contribute to bias in customer reviewsLearn how to find and download datasets from KaggleLearn how to clean dataset by removing missing rows and duplicate valuesLearn how to find correlation between customer ratings and sentimentLearn how to identify keywords that are frequently used in positive and negative customer reviewsLearn how to analyse emotional aspect of customer reviews using EmoLexLearn how to perform sentiment analysis on customer review data using TextBlobLearn how to analyse emotional aspect of tweets using NRCLexLearn how to perform sentiment analysis on twitter post data using VADERLearn how to predict sentiment of a tweet using BERTLearn how to predict sentiment of a tweet using Multinomial Naive BayesLearn how to set up Google Colab IDE
Overview
Section 1: Introduction
Lecture 1 Introduction to the Course
Lecture 2 Table of Contents
Lecture 3 Whom This Course is Intended for?
Section 2: Tools, IDE, and Datasets
Lecture 4 Tools, IDE, and Datasets
Section 3: Introduction to Sentiment Analysis
Lecture 5 Introduction to Sentiment Analysis
Section 4: How Sentiment Analysis Works?
Lecture 6 Sentiment Analysis Case Study
Section 5: Factors That Contribute to Bias in Customer Review
Lecture 7 Factors That Contribute to Bias in Customer Review
Section 6: Setting Up Google Colab IDE
Lecture 8 Setting Up Google Colab IDE
Section 7: Finding & Downloading Datasets From Kaggle
Lecture 9 Finding & Downloading Datasets From Kaggle
Section 8: Project Preparation
Lecture 10 Uploading Dataset to Google Colab
Lecture 11 Quick Overview of Hotel Review Dataset
Section 9: Cleaning Dataset by Removing Missing Values & Duplicates
Lecture 12 Cleaning Dataset by Removing Missing Values & Duplicates
Section 10: Finding Correlation Between Customer Rating and Sentiment
Lecture 13 Finding Correlation Between Customer Rating and Sentiment
Section 11: Identifying Keywords That are Frequently Used in Positive & Negative Review
Lecture 14 Identifying Keywords That are Frequently Used in Positive & Negative Review
Section 12: Analyzing Emotional Aspect of Customer Review with EmoLex
Lecture 15 Analyzing Emotional Aspect of Customer Review with EmoLex
Section 13: Performing Sentiment Analysis on Hotel Review Data with TextBlob
Lecture 16 Performing Sentiment Analysis on Hotel Review Data with TextBlob
Section 14: Analyzing Emotional Aspect of Tweets with NRCLex
Lecture 17 Analyzing Emotional Aspect of Tweets with NRCLex
Section 15: Performing Sentiment Analysis on Twitter Post Data with VADER
Lecture 18 Performing Sentiment Analysis on Twitter Post Data with VADER
Section 16: Predicting Tweet Sentiment with BERT
Lecture 19 Predicting Tweet Sentiment with BERT
Section 17: Predicting Tweet Sentiment with Multinomial Naive Bayes
Lecture 20 Predicting Tweet Sentiment with Multinomial Naive Bayes
Section 18: Conclusion & Summary
Lecture 21 Conclusion & Summary
People who are interested in performing sentiment analysis on customer reviews and tweets dataset,People who are interested in detecting emotions using NRCLex
Screenshots