Welcome to the README file for the Sentiment Analysis Android app built with Kotlin. This app is a powerful tool designed to provide users with deep insights into the sentiments and emotions expressed on Twitter. Leveraging cutting-edge technologies such as Nitter for tweet scraping and machine learning models for sentiment analysis, this app offers a comprehensive dashboard to visualize emotional trends and sentiments. Additionally, it provides a feature to analyze the sentiment and emotion of any custom sentence, further extending its utility. The app also employs the Anygraph library to draw visually appealing graphs for better data representation and user engagement.
The Sentiment Analysis Android app is meticulously crafted to offer users an immersive experience in understanding the emotions and sentiments prevalent across Twitter profiles, posts, and custom sentences. By harnessing the capabilities of Nitter for tweet scraping and sophisticated ML models for sentiment analysis, the app delivers a sophisticated dashboard that enables users to explore emotional nuances with ease and clarity.
- Twitter Sentiment Analysis: Analyze sentiments and emotions within Twitter profiles and posts.
- Nitter Integration: Utilize Nitter to scrape tweets from user profiles or trending hashtags, ensuring comprehensive data coverage.
- Comprehensive Dashboard: Generate detailed dashboards with intuitive graphs illustrating sentiment trends for deeper insights.
- Custom Sentence Analysis: Perform sentiment analysis on custom sentences to gain immediate insights into emotional tones.
- Interactive Visualizations: Visualize sentiment and emotion analysis results using the dynamic capabilities of the Anygraph library.
- Personalized Themes: Switch between light and dark themes to tailor the user experience according to preferences.
Explore the app's user interface and features through these captivating screenshots:
- Language: Kotlin
- Network Calls: Retrofit library for efficient API calls and data loading.
- UI Components:
- RecyclerView: Displays scraped tweets and sentiment analysis results.
- Anygraph: Draws interactive graphs for visualizing sentiment trends.
- Material Components: Consistent UI elements and themes for an appealing look and feel.
- Asynchronous Operations: Coroutines for handling asynchronous tasks efficiently.
- Data Scraping: Nitter is used for scraping tweets from user profiles or trending hashtags.
- Machine Learning: TensorFlow framework for building and training deep learning models for sentiment analysis.
- Web Framework: Flask is employed for building the backend of the application.
- Graph Visualization: Anygraph library is utilized to draw graphs for a more intuitive representation of sentiment trends.
- API: The backend API handles data processing and communication between the app and ML models.
For more details, visit the original Backend Repository.
To clone and run this application locally, follow these steps:
- Clone the repository:
git clone https://github.com/vish9431/Sentify.git
- Open the project in Android Studio.
- Build and run the application on your Android device or emulator.
This project is licensed under the Apache-2.0 license. See the Apache-2.0 license file for details.
Have questions or feedback? Feel free to reach out: