Fig 1.
Yearly average of the representation vector of each dimension (Dimensions are randomly sampled).
(a,b) Nanocarbon: Result of LINE 1st (a) LINE 2nd(b) (c,d) Solar cells (e,f) APS. The horizontal axis shows the publication year. The vertical axis shows the normalized value of the mean value of the representation vector published in that year.
Fig 2.
Visualization of papers in academic fields.
Papers are colored by year (left panels) and by future citations (right panels): (a) The 2D representation obtained by PCA from the LINE-1st representation of Nanocarbon is shown in this figure. Each dot represents a paper. It is colored by publication year. The group paper grows in specific directions as the year grows. (b) This figure shows only the latest (2014) year’s paper’s 2D representation. The future top 10% cited papers are colored by orange and these papers appear to gather in a specific area. (c,d) Same plot of solar cells and (e,f) APS.
Fig 3.
Distribution of IPY in set 0-citation, top 10% future citation, and other papers.
The blue line (secondary axis) corresponds to the ratio of future top 10%cited papers in each bin. (a,b) Results of nanocarbon using (a) LINE 1st and (a) LINE 2nd. (c,d) The same plot of Solar cells and (e,f) APS.
Table 1.
Correlation between features and log(future citation count + 1).
Fig 4.
Parameter sensitivity of the cutoff year Cy for the correlation between IPY and future citations.
(a) The horizontal axis shows the cutoff year Cy. The vertical axis shows the correlation between each paper’s IPY of 2014 papers and the number of 2016 citations. (b,c) This is the same plot of solar cells and APS.
Table 2.
AIPY and APY’s correlation to the growth of word frequency and results from top-N growth word predictions by changing datasets and Tf = 5, 10, 20.
Fig 5.
Outline of our citation prediction framework.
Table 3.
Datasets: Citation networks.