Movie-reviews

NLP analysis to understand public sentiment towards different films on IMDb. Implemented a pre-processing pipeline for EDA and compared multiple sentiment analysis models including TextBlob, VADER, and word2vec to identify the best approach for understanding the opinions expressed in the reviews.

Getting Started

This is an example of how you may give instructions on setting up your project locally. To get a local copy up and running follow these simple example steps.

Dataset

Only first 2 parts (1M reviews) are used for this analysis. Download dataset.

Installation

• TextBlob

  pip install -U textblob

• VADER

  pip install vaderSentiment

• NLTK

  pip install --user -U nltk

Results

Model	Accuracy
TextBlob	0.80
VADER	0.76
Word2Vec	0.87