Identifying Promising Research Topics in Computer Science

  • Rajmund KlemińskiEmail author
  • Przemyslaw Kazienko
Part of the Lecture Notes in Social Networks book series (LNSN)


In this paper, we investigate an interpretable definition of promising research topics, complemented with a predictive model. Two methods of topic identification were employed: bag of words and the LDA model, with reflection on their applicability and usefulness in the task of retrieving topics on a set of publication titles. Next, different criteria for promising topic were analyzed with respect to their usefulness and shortcomings. For verification purposes, the DBLP data set, an online open reference of computer science publications, is used. The presented results reveal potential of the proposed method for identification of promising research topics.


Research prediction Promising topic Topic modelling DBLP 



This work was partially supported by the National Science Centre, Poland, project no. 2016/21/B/ST6/01463 and by European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant no. 691152 (RENOIR); by the Polish Ministry of Science and Higher Education fund for supporting internationally co-financed projects in 2016-2019, no. 3628/H2020/2016/2.


  1. 1.
    Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. Adv. Neural Inf. Proces. Syst. 1, 601–608 (2002)Google Scholar
  2. 2.
    Glänzel, W., Thijs, B.: Using ‘core documents’ for detecting and labelling new emerging topics. Scientometrics 91(2), 399–416 (2012)CrossRefGoogle Scholar
  3. 3.
    He, Q., Chen, B., Pei, J., Qiu, B., Mitra, P., Giles, L.: Detecting topic evolution in scientific literature: how can citations help? In: Proceedings of the 18th ACM Conference on Information and Knowledge Management, CIKM ’09, pp. 957–966 (2009)Google Scholar
  4. 4.
    Hong, L., Davison, B.D.: Empirical study of topic modeling in twitter. In: Proceedings of the First Workshop on Social Media Analytics, SOMA ’10, pp. 80–88 (2010)Google Scholar
  5. 5.
    Hurtado, J.L., Agarwal, A., Zhu, X.: Topic discovery and future trend forecasting for texts. J. Big Data 3(1), 7 (2016)CrossRefGoogle Scholar
  6. 6.
    Loper, E., Bird, S.: Nltk: The natural language toolkit. In: Proceedings of the ACL-02 Workshop on Effective Tools and Methodologies for Teaching Natural Language Processing and Computational Linguistics - Volume 1, ETMTNLP ’02, pp. 63–70 (2002)Google Scholar
  7. 7.
    Lu, Y., Zhang, P., Liu, J., Li, J., Deng, S.: Health-related hot topic detection in online communities using text clustering. PLoS One 8(02), e56221 (2013)CrossRefGoogle Scholar
  8. 8.
    Mund, C., Neuhäusler, P.: Towards an early-stage identification of emerging topics in science–the usability of bibliometric characteristics. J. Informetrics 9(4), 1018–1033 (2015)CrossRefGoogle Scholar
  9. 9.
    Prabhakaran, V., Hamilton, W.L., McFarland, D.A., Jurafsky, D.: Predicting the rise and fall of scientific topics from trends in their rhetorical framing. In: ACL (2016)Google Scholar
  10. 10.
    Wang, Y., Joo, S., Lu, K.: Exploring topics in the field of data science by analyzing Wikipedia documents: a preliminary result. Proc. Am. Soc. Inform. Sci. Technol. 51(1), 1–4 (2014)Google Scholar
  11. 11.
    Zhang, B., Guan, X., Khan, M.J., Zhou, Y.: A time-varying propagation model of hot topic on {BBS} sites and blog networks. Inform. Sci. 187, 15–32 (2012)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Computational Intelligence, ENGINE - The European Centre for Data Science, Faculty of Computer Science and ManagementWroclaw University of Science and TechnologyWroclawPoland

Personalised recommendations