Development of Machine Learning-Based Text Processing Tool for Abstract of Physical Chemistry Papers
Yuika WATARI, Koji Okuwaki, Yuji Mochizuki · Journal of Computer Chemistry Japan · 2019
We have developed a text processing tool consisting of several machine learning-related programs such as TreeTagger and Doc2Vec. This system was applied to a number of abstracts of a couple of physical chemistry journals (Chemical Physics Letters and American Journal of Physics). The degree of similarity of contents was then made evaluatable as a guide for papers to be checked for a certain topic.