This is an extension of my master project at the University of Duisburg-Essen. The motivation of the master project was to detect the propaganda articles in websites. The project was highly successful. This is a personal project to make the propaganda detection at article level in a personalized web application. Users can input a text located in home page and predict using a binary classifier ("propaganda" or "non-propaganda").
With the rise of social media everybody is free to share their thoughts and ideas. In addition, various news media suffer from the unethical practice to deliver deliberate disinformation. Therefore, with great online speech freedom, an even greater responsibility arises – to be able to differentiate between fake, i.e. propagandistic type of text, and an objective, evidence-based view.
- guide to create the model
- make links to the pretrained model and vectorizers
- make the website ready
- create a docker image with dependencies installed and upload it in docker hub
- create a docker image for this web application