Overview / Usage

Sentiment Analysis is a popular Natural Language Processing (NLP) task that aims to classify the sentiment of a given text as either positive, negative or neutral. In this project, IMDb reviews are used to train and evaluate a Sentiment Analysis model using the oneDAL toolkit from Intel.

​

The IMDb dataset consists of 5,000 movie reviews, which are labeled as either positive or negative. The oneDAL toolkit is used to preprocess the data and build a Naive Bayes model for sentiment analysis. The oneDAL library provides efficient and optimized algorithms for data preprocessing, feature engineering, and model training, which helps to achieve high accuracy in classification tasks.

​

The project involves several steps, including data cleaning, feature extraction, model training, and evaluation. First, the dataset is preprocessed using oneDAL algorithms, such as data normalization and feature scaling, to prepare it for training. Next, feature extraction techniques such as Bag-of-Words and TF-IDF are applied to transform the text data into numerical features.

​

After that, the model is trained using the oneDAL library, which provides a scalable and efficient implementation for large datasets. Finally, the model is evaluated on a test dataset to measure its accuracy and performance.

​

The results of the Sentiment Analysis using oneDAL on IMDb reviews project show that the model achieved high accuracy in classifying the sentiment of the reviews, with an accuracy score of over 80.3%. This project demonstrates the effectiveness of oneDAL library for NLP tasks and highlights its potential in building efficient and accurate machine learning models.

Repository

https://github.com/rish4522/Sentiment_Analysis_using_IMDB_Reviews

Collaborators

2 Results

* Sort

Most Popular Number of Activities Number of Projects Recently Joined

• Projects 1
• Followers 1

Rishabh Tripathi Dev

Follow

• Projects 1
• Followers 1

Advaith Rajesh

Follow

Bengaluru, Karnataka

2 Results