fake-paper-detection

The null hypothesis is a typical statistical theory which suggests that no statistical relationship and significance exists in a set of given single observed variable, between two sets of observed data and measured phenomena. In this project, the null hypothesis is that there is no difference between the real and fake in terms of the distribution of average distance of paper and its references. As the T-Test, the t-statistic is 1781.45 and the p-value is 0.00. The final T-Test rejects null hypothesis and the distance between paper and its references can be used as an indicator of whether the paper could be fake or real. So, we can conclude that in general, real paper and its reference have smaller average difference than fake paper and its references.

In conclusion, we have proved our previous assumption that in general fake paper and its references are less related whereas real paper and its references are more related to each other.