Skip to content

NgHuyn/Sentiment-Analysis

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 

Repository files navigation

Introduction

In the dynamic landscape of today's digital age, the vast amount of textual data generated on online platforms provides a rich source of valuable insights. Understanding the sentiment behind this data is crucial for businesses, organizations, and individuals alike. Sentiment analysis, also known as opinion mining, is the process of extracting and deciphering sentiments expressed in text data to comprehend the emotional tone and subjective opinions of individuals or groups.

Our Sentiment Analysis Project seeks to harness the power of natural language processing and machine learning techniques to analyze and categorize sentiments within textual content. By leveraging advanced algorithms, we aim to provide a comprehensive understanding of public opinions, customer feedback, or social media discourse. This project holds the potential to unveil nuanced insights, helping businesses make informed decisions, enhance customer satisfaction, and gain a competitive edge in an increasingly interconnected and opinion-driven digital world.

Table of content

  1. Data collecting
  2. EDA
  3. Data preprocessing
  4. Data modeling
  5. GridSearchCV and Cross Validation
  6. Pipeline and web UI

Techniques

Using text preprocessing techniques (stopwords, lemmatization, stemming,..) and TF-IDF technique to build 3 models: Logistic Regression, Random Forest and Naive Bayes. Besides, we use GridSearchCV and Cross Validation to choose the best parameter for each model and evaluate their effectiveness in sentiment analysis. After completing the model building and evaluation, proceed to attach the entire process to the pipeline for application.

Conclusion

In conclusion, our Sentiment Analysis Project stands at the forefront of leveraging cutting-edge technology to decode the intricate tapestry of human emotions embedded in textual data. As we navigate the realms of natural language processing and machine learning, our project promises a nuanced understanding of sentiments expressed across diverse digital platforms.

Finally, thanks for the contributions of the team members to complete this project. Even though we can made mistakes, this is a project that the whole team tried our best to complete.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published