Welcome to FactIT
Design and develop a technological solution/software tool for Tracking & Tracing Fake News and its origin using official sources as the input filter. The solution should have a mechanism to mitigate the impact of the spread of Fake News by auto-populating the fake news spreaders’ inboxes with the official/authenticated news content.
FactIT allows users to filter information by day, time, and region, making educational content more accessible and relevant.
A user-friendly chatbot guides students through the application, providing assistance and educational insights.
Leveraging Generative AI, Machine Learning, and Deep Learning models, FactIT determines the authenticity of news articles, educating users on distinguishing between true and false information.
For each verified news article, FactIT provides links to credible sources, empowering students to follow a study path based on reliable information.
The auto-populating feature allows users to automatically share verified news, reducing the spread of misinformation and elevating the overall quality of education.
- Generative AI
- Machine Learning
- Deep Learning
- Flask
- JavaScript
- HTML
- CSS
- Bootstrap
- BeautifulSoup
- Selenium
- Random Forest: News title classification
- Naive Bayes: Clickbait detection
- Transformers: Named entity recognition for names and places
- Transformers: Subjectivity analysis
- BERT: News similarity assessment
- NER Pipeline: Loading the named entity recognition model
Users can enter the news they want to verify. FactIT processes the entered news and provides an assessment of its authenticity, enriching the quality of the dataset.
The entry point allows users to input news articles into the system.
FactIT evaluates the entered news, indicating whether it is true or false. It also provides information and credibility details, enhancing user trust in the information.
Users can access a curated news feed enriched with verified information for their study purposes.
FactIT provides options to filter the news feed based on date and region, tailoring the information to specific user requirements.
FactIT comes with several distinctive features that set it apart from other education hubs and resources.
The project includes an interactive chatbot designed to assist users in understanding the application. If a user is confused, the chatbot provides guidance, enhancing the overall user experience.
FactIT introduces an auto-populating feature using Selenium. It alerts students if they are reading misleading or incorrect news, fostering a more informed educational experience.
The entire project is centered around Natural Language Processing (NLP), leveraging cutting-edge technologies to enhance the quality of news verification. The images below illustrate the NLP process.
-
Clone the repository:
git clone https://github.com/PulijalaSaiRahul/Fake-News-Detection-System.git
-
Install dependencies:
cd GFake-News-Detection-System pip install -r requirements.txt
-
Run the application:
python app.py
-
Open your web browser and navigate to the provided local URL.
-
You can give input as text form or else the input can be given as image where we will take the input image and using OCR we will extract the text from image 4.Please give images which has news or some text inside it
Users can customize the project by modifying the Bard API key. In case users encounter issues, they can replace the key in the configuration file.
- Database Integration: Future plans include connecting the project to a database for data storage and retrieval.
- Power BI Integration: Explore options for enhancing interactivity by integrating the project with Power BI.
- Generative AI
- Google Bard
Pulijala Sai Rahul Vempati Sai Vishal Mamilla Thanish kumar