Data for: Does deep learning help topic extraction? A kernel k-means clustering method with word embedding

Published: 24 September 2018| Version 1 | DOI: 10.17632/kg5dcdt9b6.1
Yi Zhang,
Hongshu Chen,
Feng Liu,
Guangquan Zhang,
qian liu,
Alan Porter,
Jie Lu


The 4770 dataset includes 4770 articles in the Web of Science database, covering 10 disciplines, such as artificial intelligence, business, history, and chemistry. The 577 dataset includes 577 proposals granted by the National Science Foundation of the United States, and all the 577 proposals are within the area of computer science but are in different sub areas of computer science. The 6767 dataset includes 6767 articles published in Journal of the Association for Information Science and Technology, Journal of Informetrics, and Scientometrics from 2000 to 2016. No labels are given for this dataset.



Computer Science, Bibliometrics