1 -Course Overview (2.72 MB)
2 -Introducing Sentiment Analysis (7.35 MB)
3 -Two Case Studies (9.64 MB)
4 -Polarity Detection for Sentiment Analysis (7.03 MB)
5 -Setting up a Binary Classification Problem (4.95 MB)
6 -Rule-based and ML-based Binary Classifiers (9.73 MB)
10 -Making It (Slightly More) Real (8.25 MB)
11 -Building Is Hard, Using Is Easy (4.52 MB)
7 -Starting Simple, Starting Simplistic (10.62 MB)
8 -Limitations of a Simplistic Approach (3.9 MB)
9 -A More Realistic Rule-based Algorithm (6.96 MB)
12 -Introducing VADER (10.51 MB)
13 -Punctuation, Negation, Emphasis, and Contrast (7.92 MB)
14 -Classifying Movie Reviews with VADER (16.43 MB)
15 -Introducing Sentiwordnet (8.77 MB)
16 -Classifying Movie Reviews with Sentiwordnet (12.94 MB)
17 -Exploring ML-based Approaches (5.9 MB)
18 -The Intuition Behind Bayes Theorem (6.91 MB)
19 -Naive Bayes for Classification Problems (9.08 MB)
20 -Applying Bayes Theorem (8.48 MB)
21 -Support Vector Machines (7.05 MB)
22 -The Importance of Feature Extraction (8.9 MB)
23 -An Outline of Implementing Naive Bayes (7.68 MB)
24 -Data Transformation for nltk (7.47 MB)
25 -Python Implementation of Naive Bayes (11.26 MB)
26 -Comparing VADER, Sentiwordnet, and Naive Bayes (5.51 MB)
building-sentiment-analysis-systems-python (2.25 MB)