Skip to content

The purpose of this project is to make up a prediction model where we will be able to predict whether a recommendation is positive or negative.

Notifications You must be signed in to change notification settings

ssomani7/Sentiment_Analysis_Project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Introduction

The purpose of this project is to make up a prediction model where we will be able to predict whether a recommendation is positive or negative. In this project, we will not focus on the Score, but only the positive/negative sentiment of the recommendation.

To do so, we will work on Amazon's recommendation dataset, we will build a Term-doc incidence matrix using term frequency and inverse document frequency ponderation. When the data is ready, we will load it into predicitve algorithms, mainly naïve Bayesian and regression.

Dataset


Dataset can be downloaded from this link. After downloading the data copy it to the 'resources' folder.

Installation

The application can be run in one of the two ways, either using Python Interpreter or using Jupyter Notebook.

Python Environment

This project require Python 3.6 interpreter.

To use the Python interpreter to run the project, first install the python packages being used in this project.
pip3 install -r requirements.txt
or
pip install -r requirements.txt

To run the application
$python P3

Conda Environment

The project requires Anaconda 3.

To install Anaconda3 download the shell script from Anaconda website.
Run the following command
bash Anaconda-latest-Linux-x86_64.sh

Run the following to create environment and install packages
conda env create -f project_env.yml

Run the following to run the Jupyter Notebook
jupyter notebook

Select the '.ipynb' file.

About

The purpose of this project is to make up a prediction model where we will be able to predict whether a recommendation is positive or negative.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published