Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[README Enhancement]: ChatGPT-Based Tweets Sentiment Analysis Using Deep Learning #534

Merged
merged 4 commits into from
May 12, 2024
Merged

[README Enhancement]: ChatGPT-Based Tweets Sentiment Analysis Using Deep Learning #534

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ef833c5
Enhancement: increased readability, information
jindalpriyanshu101 May 12, 2024
b798351
Fixed requirement.txt
jindalpriyanshu101 May 12, 2024
d7c3048
Rename requirement.txt to requirements.txt
jindalpriyanshu101 May 12, 2024
8fcc3e0
Rename Readme.md to README.md
jindalpriyanshu101 May 12, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
62 changes: 33 additions & 29 deletions ChatGPT Based Tweets Sentiment Analysis Using DL/Readme.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,64 +1,68 @@
## **PROJECT TITLE**
ChatGPT-Based Tweets Sentiment Analysis Using Deep Learning

GOAL
## 🎯 **Goal**

The aim of this project is to analyze the sentiments of the tweets made on/against ChatGPT.

DATASET
## 🧵 **Dataset**

https://www.kaggle.com/datasets/charunisa/chatgpt-sentiment-analysis
Link to dataset: https://www.kaggle.com/datasets/charunisa/chatgpt-sentiment-analysis

DESCRIPTION
## 🧾 **Description**

Sentiment analysis on ChatGPT tweets involves using NLP to analyze emotions and attitudes expressed in tweets by the language model. It categorizes tweets as good, bad, or neutral, providing insights into the overall emotional tone of the content. However, it may not fully capture nuances like humor and sarcasm. Regular updates improve accuracy in understanding human emotions.

WHAT I HAD DONE
## 🧮 **What I had done!**

The code is an end-to-end sentiment analysis project, covering data loading, cleaning, preprocessing, model training, evaluation, and visualization. It utilizes different machine learning models to compare their performance on sentiment analysis tasks.

MODELS USED
## 🚀 **Models Implemented**

CNN, LSTM, VADER
1. **CNN:** Convolutional Neural Networks, are specialized neural networks for image processing. They automatically learn features from images through layers like convolutional and pooling. They've revolutionized computer vision tasks like object detection and facial recognition.

2. **LSTM:** Long Short-Term Memory, is utilized for tweet analysis. It can capture the sequential nature of tweets, retaining context over varying tweet lengths. This enables better understanding of tweet sentiment, topic trends, and user engagement patterns. LSTM's ability to remember long-term dependencies makes it ideal for processing dynamic social media data like tweets.

EDA
![Screenshot 2024-01-17 160308](https://github.com/abhisheks008/DL-Simplified/assets/105275283/ee0647fe-5692-42ef-ac30-cbcc5a78d34c)
3. **VADER:** VADER is a sentiment analysis tool specifically designed for social media text like tweets. It measures the polarity of text, capturing both positive and negative sentiment as well as the intensity of emotions expressed. When applied to ChatGPT-based tweets, VADER can help analyze the emotional tone of the generated text, providing insights into the sentiment conveyed.

![Screenshot 2024-01-17 160335](https://github.com/abhisheks008/DL-Simplified/assets/105275283/12616fea-08c1-4c46-a333-afeced357bac)
## 📊 **Exploratory Data Analysis Results**
EDA(Exploratory Data Analysis) visualization:

![Screenshot 2024-01-17 160358](https://github.com/abhisheks008/DL-Simplified/assets/105275283/23f82be1-a56e-4700-95d7-fc85deeb4c76)
1. ![Screenshot 2024-01-17 160308](https://github.com/abhisheks008/DL-Simplified/assets/105275283/ee0647fe-5692-42ef-ac30-cbcc5a78d34c)

![Screenshot 2024-01-17 160411](https://github.com/abhisheks008/DL-Simplified/assets/105275283/5748d3f3-8f66-4587-a01c-8d3002c6d51f)
2. ![Screenshot 2024-01-17 160335](https://github.com/abhisheks008/DL-Simplified/assets/105275283/12616fea-08c1-4c46-a333-afeced357bac)

![Screenshot 2024-01-17 160425](https://github.com/abhisheks008/DL-Simplified/assets/105275283/a8128762-8b2b-4c5e-ac1b-2f5305f9fa8e)
3. ![Screenshot 2024-01-17 160358](https://github.com/abhisheks008/DL-Simplified/assets/105275283/23f82be1-a56e-4700-95d7-fc85deeb4c76)

![Screenshot 2024-01-17 160438](https://github.com/abhisheks008/DL-Simplified/assets/105275283/abc2f903-c6cd-4350-b355-1a985ba0d8bf)
4. ![Screenshot 2024-01-17 160411](https://github.com/abhisheks008/DL-Simplified/assets/105275283/5748d3f3-8f66-4587-a01c-8d3002c6d51f)

![Screenshot 2024-01-17 160524](https://github.com/abhisheks008/DL-Simplified/assets/105275283/1b02e83c-4bfc-42b4-a331-813c65c2dc84)
5. ![Screenshot 2024-01-17 160425](https://github.com/abhisheks008/DL-Simplified/assets/105275283/a8128762-8b2b-4c5e-ac1b-2f5305f9fa8e)

![Screenshot 2024-01-17 160537](https://github.com/abhisheks008/DL-Simplified/assets/105275283/ed50d915-a997-41ba-9ef4-b694a9b40e9f)
6. ![Screenshot 2024-01-17 160438](https://github.com/abhisheks008/DL-Simplified/assets/105275283/abc2f903-c6cd-4350-b355-1a985ba0d8bf)

![Screenshot 2024-01-17 160548](https://github.com/abhisheks008/DL-Simplified/assets/105275283/70599d6a-d251-42c8-b30b-6085f3f34420)
7. ![Screenshot 2024-01-17 160524](https://github.com/abhisheks008/DL-Simplified/assets/105275283/1b02e83c-4bfc-42b4-a331-813c65c2dc84)

8. ![Screenshot 2024-01-17 160537](https://github.com/abhisheks008/DL-Simplified/assets/105275283/ed50d915-a997-41ba-9ef4-b694a9b40e9f)

![Screenshot 2024-01-17 160557](https://github.com/abhisheks008/DL-Simplified/assets/105275283/a5335f08-3851-4534-b220-9a1517090ef3)
9. ![Screenshot 2024-01-17 160548](https://github.com/abhisheks008/DL-Simplified/assets/105275283/70599d6a-d251-42c8-b30b-6085f3f34420)

![Screenshot 2024-01-17 160607](https://github.com/abhisheks008/DL-Simplified/assets/105275283/516b68ed-933d-488f-b5f2-c4de7145a1b8)
10. ![Screenshot 2024-01-17 160557](https://github.com/abhisheks008/DL-Simplified/assets/105275283/a5335f08-3851-4534-b220-9a1517090ef3)

LIBRARIES NEEDED
11. ![Screenshot 2024-01-17 160607](https://github.com/abhisheks008/DL-Simplified/assets/105275283/516b68ed-933d-488f-b5f2-c4de7145a1b8)

Mentioned in requirements.text file.
## 📚 **Libraries Needed**

VISUALIZATION
Mentioned in **requirements.txt** file.
- To install, write the following command in your working directory's terminal:
`pip install -r requirements.txt`

ACCURACIES
CNN: 0.8841029004083822
LSTM : 0.8942677437624825
## 📈 **Performance of the Models based on the Accuracy Scores**
- CNN: 0.8841029004083822
- LSTM : 0.8942677437624825


CONCLUSION
## 📢 **Conclusion**
In conclusion, the code serves as a comprehensive sentiment analysis project, covering data preprocessing, model selection, training, evaluation, and visualization. It demonstrates the application of different machine learning models to analyze sentiments in Twitter data, offering a useful framework for similar natural language processing tasks.

YOUR NAME

## ✒️ **Your Signature**
Jigyasa Karakoti

Loading
Loading