Predicting research trends with semantic and neural networks with an application in quantum physics
Code for the paper: https://www.pnas.org/content/early/2020/01/13/1914370116/tab-article-info / https://arxiv.org/abs/1906.06843
by Mario Krenn (mario.krenn@univie.ac.at) and Anton Zeilinger (anton.zeilinger@univie.ac.at)
We show an implementation in MATLAB and in python for creating a semantic network from data, and making predictions into the future.
CreateAndAnalyseSEMNET
Contains a simple example, how to start from APS and arXiv files to create a Semantic Networks, calculate network theoretic properties, and make predictions
PersonalizedSuggestions
Shows how to make personalized surprising predictions from personal papers, SemNet and the neural network predictions
FullSemNet
Full concept list with 6372 entries, and the Semantic Network which is 6372x6372 entries with time information about concept emergence and connection emergence