Predatory Journals exploit authors by soliciting publication fees without providing legitimate peer-review or editing services. These journals often bypass proper academic standards, offering quick manuscript publishing turnaround times. Scholars may unknowingly fall victim to these predatory practices, while some authors might be aware of the substandard or even fraudulent nature of the journal.
To address this issue, a model was implemented for Predatory Journal Detection using the Decision Tree algorithm. This model is integrated into a user-friendly website developed using Django. The primary goal of this project is to automate the process of detecting predatory journals, utilizing specific parameters that are crucial in evaluating the credibility of academic publications.
Decision Tree Model: Our system incorporates a Decision Tree algorithm to analyze various parameters and make predictions regarding the predatory nature of a journal.
Django Web Application: The detection model is seamlessly integrated into a Django web application, providing an accessible and interactive platform for users to evaluate journals.
The Decision Tree model in our system evaluates various parameters commonly associated with predatory journals. By analyzing these factors, the model provides insights into the likelihood of a journal being predatory.
Users can input relevant information about a journal into the web application, and the Decision Tree model will generate predictions based on the provided data.