Detection of Predatory Journal Using Machine Learning and Django

Recently there are lots of piracy events happening in various areas. Predatory Journals take advantage of authors by asking them to publish for a fee without providing peer-review or editing services. To tackle this we have created a solution using the concept of machine learning and Django.

Predatory Journals take advantage of authors by asking them to publish by paying their fees, without providing peer-review or editing services. Because predatory publishers do not follow the proper academic standards for publishing, they usually offer a quick turnaround on publishing a manuscript. They are regarded as predatory because scholars are tricked into publishing with them, although some authors may be aware that the journal is of poor quality or even fraudulent. In contrast, high-quality academic journals take longer to publish articles because they go through a proper peer review and copy-editing process. To prevent these frauds we’ve created an application by which we can determine whether a journal is predatory or not. The application is created with the help of the python framework Django which is used for maintaining individual journal records with its parameters. The determination of a predatory journal is done by using a machine learning algorithm, i.e, Decision tree algorithm. Here the model is trained with journal name and its parameters and saved as a file so that later on whenever needed, we can load the trained model directly without re-training the model. After combining the database and ML algorithm, we get the journal details with the result after searching the journal name in the user interface.

Considering the current situation, the detection of journals is done usually in manual mode which takes a lot of time and we have converted the solution into a digital model which takes very little to no time for detection of predatory. Moreover, our solution is efficient in terms of performance.