https://github.com/pratishtha-abrol/sentimentanalysis

Logistic Regression: A sentiment analysis case study
https://github.com/pratishtha-abrol/sentimentanalysis

logistic-regression nltk-python scikit-learn sentiment-analysis

Last synced: 18 days ago
JSON representation

Logistic Regression: A sentiment analysis case study

• Host: GitHub
• URL: https://github.com/pratishtha-abrol/sentimentanalysis
• Owner: pratishtha-abrol
• Created: 2020-06-01T15:32:15.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2020-06-01T17:05:35.000Z (over 4 years ago)
• Last Synced: 2024-10-24T20:07:12.490Z (2 months ago)
• Topics: logistic-regression, nltk-python, scikit-learn, sentiment-analysis
• Language: Jupyter Notebook
• Homepage:
• Size: 24.7 MB
• Stars: 0
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# SentimentAnalysis

Logistic Regression: A sentiment analysis case study

## Key Concepts

* Build and employ a logistic regression classifier using scikit-learn

* Clean and pre-process data

* Perform feature extraction with nltk

* Tune model hyperparameters and evaluate model accuracy

## Dataset

IMDB movie reviews dataset

http://ai.stanford.edu/~amaas/data/sentiment

Contains 25000 positive and 25000 negative reviews 

Contains at most reviews per movie

At least 7 stars out of 10 : positive (label = 1)

At most 4 stars out of 10 : negative (label = 0)

50/50 train/test split

Evaluation accuracy

## Features: bag of 1-grams with TF-IDF values:

Extremely sparse feature matrix - close to 97% are zeros

## Model: Logistic regression

p(y=1|x)=σ(w.Tx)

Linear classification model

Can handle sparse data

Fast to train

Weights can be interpreted