{"id":32455561,"url":"https://github.com/venkat-0706/twalyze","last_synced_at":"2026-05-07T19:18:40.371Z","repository":{"id":293446610,"uuid":"960785122","full_name":"venkat-0706/Twalyze","owner":"venkat-0706","description":"Twitter sentiment analysis project using machine learning to classify tweets and understand audience mood, opinions, and behavior trends in real-time.","archived":false,"fork":false,"pushed_at":"2025-05-15T10:59:38.000Z","size":25,"stargazers_count":10,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-26T08:10:50.480Z","etag":null,"topics":["logistic-regression","machine-learning","model-evaluation","naive-bayes-classifier","pandas","python","scikitlearn-machine-learning","tfidf-vectorizer","tokenization"],"latest_commit_sha":null,"homepage":"https://colab.research.google.com/github/venkat-0706/Twalyze/blob/main/Twitter_Sentiment_Analysis_Using_Machine_Learning.ipynb","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/venkat-0706.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-04-05T04:09:59.000Z","updated_at":"2025-10-21T11:42:50.000Z","dependencies_parsed_at":"2025-05-15T11:57:27.405Z","dependency_job_id":null,"html_url":"https://github.com/venkat-0706/Twalyze","commit_stats":null,"previous_names":["venkat-0706/twalyze"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/venkat-0706/Twalyze","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/venkat-0706%2FTwalyze","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/venkat-0706%2FTwalyze/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/venkat-0706%2FTwalyze/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/venkat-0706%2FTwalyze/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/venkat-0706","download_url":"https://codeload.github.com/venkat-0706/Twalyze/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/venkat-0706%2FTwalyze/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32752258,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-07T02:14:30.463Z","status":"ssl_error","status_checked_at":"2026-05-07T02:14:29.405Z","response_time":62,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["logistic-regression","machine-learning","model-evaluation","naive-bayes-classifier","pandas","python","scikitlearn-machine-learning","tfidf-vectorizer","tokenization"],"created_at":"2025-10-26T08:03:06.036Z","updated_at":"2026-05-07T19:18:40.367Z","avatar_url":"https://github.com/venkat-0706.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Twalyze\nHere is the final version of your **GitHub `README.md`** with both **training accuracy (80%)** and **testing accuracy (79%)** clearly mentioned:\n\n---\n\n````markdown\n# 🐦 Twitter Sentiment Analysis Using Machine Learning\n\nThis project aims to analyze and classify sentiments expressed in tweets related to various airlines. It applies machine learning techniques to categorize each tweet as **Positive**, **Negative**, or **Neutral** based on its textual content.\n\n---\n\n## 📌 Objective\n\nTo build a machine learning model that classifies the sentiment of tweets using Natural Language Processing (NLP) and vectorization techniques.\n\n---\n\n## 📂 Dataset\n\nThe dataset used is `train.csv`, containing the following key columns:\n\n- `tweet_id` – Unique ID for each tweet  \n- `airline` – The airline company mentioned  \n- `airline_sentiment` – The sentiment label (positive, negative, neutral)  \n- `text` – The content of the tweet  \n\n---\n\n## 🧰 Libraries Used\n\n- `pandas`, `numpy` – Data manipulation  \n- `matplotlib`, `seaborn` – Data visualization  \n- `nltk` – Text preprocessing  \n- `sklearn` – Machine learning models and evaluation  \n- `wordcloud` – Word cloud visualization  \n\n---\n\n## 🔄 Workflow\n\n### 1. **Data Preprocessing**\n- Lowercasing text  \n- Removing URLs, mentions, hashtags, punctuations  \n- Removing stopwords  \n- Tokenization and Lemmatization (using NLTK)  \n\n### 2. **Exploratory Data Analysis**\n- Visualizing sentiment distribution  \n- Airline-wise sentiment analysis  \n- Word clouds for each sentiment category  \n\n### 3. **Feature Extraction**\n- TF-IDF Vectorization of cleaned text  \n\n### 4. **Model Training**\nTrained the following classifiers:\n- Logistic Regression  \n- Naive Bayes  \n- Random Forest  \n- Support Vector Machine (SVM)  \n\n\u003e 📈 **Best Model Training Accuracy: ~80%**  \n\u003e 🧪 **Best Model Testing Accuracy: ~79%**\n\n### 5. **Model Evaluation**\nUsed the following metrics:\n- Accuracy  \n- Confusion Matrix  \n- Classification Report  \n\n---\n\n## ✅ Results\n\nThe best-performing model achieved:\n- **Training Accuracy:** ~80%  \n- **Testing Accuracy:** ~79%  \n\nThese results indicate strong model performance with minimal overfitting.\n\n---\n\n## 💡 Possible Improvements\n\n- Integrate deep learning models like LSTM for better results  \n- Add real-time tweet scraping using Tweepy (Twitter API)  \n- Use Word2Vec or transformer-based embeddings (like BERT)  \n- Perform cross-validation for better model reliability  \n\n---\n\n## 📊 Visualizations\n\n- Word clouds for Positive, Negative, Neutral tweets  \n- Bar charts for sentiment distribution across airlines  \n- Confusion matrices for each ML model  \n\n---\n\n## 🚀 Getting Started\n\n1. Clone the repo:\n   ```bash\n   git clone https://github.com/venkat-0706/Twalyze.git\n````\n\n2. Install dependencies:\n\n   ```bash\n   pip install -r requirements.txt\n   ```\n\n3. Run the notebook:\n   Open the Colab notebook [here](https://colab.research.google.com/github/venkat-0706/Twalyze/blob/main/Twitter_Sentiment_Analysis_Using_Machine_Learning.ipynb)\n\n---\n\n## 📬 Contact\n\nCreated by [@venkat-0706](https://github.com/venkat-0706)\nFeel free to reach out for suggestions or collaborations!\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvenkat-0706%2Ftwalyze","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvenkat-0706%2Ftwalyze","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvenkat-0706%2Ftwalyze/lists"}