Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2018 May 21;13(5):e0197260.
doi: 10.1371/journal.pone.0197260. eCollection 2018.

Detecting trends in academic research from a citation network using network representation learning

Kimitaka Asatani  1 , Junichiro Mori  1 , Masanao Ochi  1 , Ichiro Sakata  1
Affiliations

Detecting trends in academic research from a citation network using network representation learning

Kimitaka Asatani et al. PLoS One. .

Abstract

Several network features and information retrieval methods have been proposed to elucidate the structure of citation networks and to detect important nodes. However, it is difficult to retrieve information related to trends in an academic field and to detect cutting-edge areas from the citation network. In this paper, we propose a novel framework that detects the trend as the growth direction of a citation network using network representation learning(NRL). We presume that the linear growth of citation network in latent space obtained by NRL is the result of the iterative edge additional process of a citation network. On APS datasets and papers of some domains of the Web of Science, we confirm the existence of trends by observing that an academic field grows in a specific direction linearly in latent space. Next, we calculate each node's degree of trend-following as an indicator called the intrinsic publication year (IPY). As a result, there is a correlation between the indicator and the number of future citations. Furthermore, a word frequently used in the abstracts of cutting-edge papers (high-IPY paper) is likely to be used often in future publications. These results confirm the validity of the detected trend for predicting citation network growth.

PubMed Disclaimer

Conflict of interest statement

The authors have declared that no competing interests exist.

Figures

Fig 1
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
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
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.
Fig 4
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.
Fig 5
Fig 5. Outline of our citation prediction framework.
See this image and copyright information in PMC

References

    1. Martin BR. The origins of the concept of ‘foresight’in science and technology: An insider’s perspective. Technological Forecasting and Social Change. 2010;77(9):1438–1447. doi: 10.1016/j.techfore.2010.06.009 - DOI
    1. Miles I. The development of technology foresight: A review. Technological Forecasting and Social Change. 2010;77(9):1448–1456. doi: 10.1016/j.techfore.2010.07.016 - DOI
    1. Singh VK, Uddin A, Pinto D. Computer science research: The top 100 institutions in India and in the world. Scientometrics. 2015;104(2):529–553. doi: 10.1007/s11192-015-1612-8 - DOI
    1. Garfield E. The history and meaning of the journal impact factor. Jama. 2006;295(1):90–93. doi: 10.1001/jama.295.1.90 - DOI - PubMed
    1. Yan R, Tang J, Liu X, Shan D, Li X. Citation count prediction: learning to estimate future citations for literature. In: Proceedings of the 20th ACM international conference on Information and knowledge management. ACM; 2011. p. 1247–1252.

Publication types