Research frontier is the focus of scientific frontier and guides the direction of scientific development. It is of great significance for the state, institutions and researchers to grasp the research frontier in a timely and accurate manner. Based on LDA model, this paper uses Python language to carry out standardized processing, stop words removal, stem extraction and word shape restoration on foreign artificial intelligence data from 2013 to 2017. The processed data are imported into LDA model to output topic—vocabulary matrix and document—topic matrix. The topic is de-scribed on the basis of the topic—vocabulary matrix, and the research frontier is calculated in the light of the document topic matrix and the con-structed frontier identification index, the research frontier of artificial in-telligence abroad is obtained, which includes three categories: computer vision research, application of artificial intelligence in various fields and data mining and clustering research.
Cite this paper
Xie, T. , Qin, P. and Yan, J. (2018). Research on Artificial Intelligence Frontier Recognition Based on LDA. Open Access Library Journal, 5, e5005. doi: http://dx.doi.org/10.4236/oalib.1105005.
Yu, H.Q., Cao, J.J. and Wang, Y.F. (2018) Frontier Analysis of International Artificial Intelligence Research from the Perspective of Information Science. Intelligence magazine, 37, 21-26.
Meho, L.I. and Yang, K. (2007) Impact of Data Sources on Citation Counts and Rankings of Lis Faculty: Web of Science versus Scopus and Google Scholar. Journal of the American Society for Information Science & Technology, 58, 2105-2125. https://doi.org/10.1002/asi.20677
Loper, E. and Steven (2002) Nltk: The Natural Language Toolkit. ETMTNLP’02 Proceedings of the ACL-02 Workshop on Effective Tools and Methodologies for Teaching Natural Language Processing and Computational Linguistics, Philadelphia, Pennsylvania, 7 July 2002, 63-70. https://doi.org/10.3115/1118108.1118117
Hu, J.M. and Chen, G. (2014) Mining and Evolution of Centent Topics Based on Dynamic LDA. Library and Information Work, 58, 138-142. https://doi.org/10.13266/j.issn.0252-3116.2014.02.023
Guan, P., Wang, Y.F. and Fu, Z. (2016) Effect Analysis of Scientific Literature Topic Extraction Based on LDA Topic Model with Different Corpus. Library and Information Service, 2, 112-121. https://doi.org/10.13266/j.issn.0252-3116.2016.02.018
Stevens, K., Kegelmeyer, P., Andrzejewski, D., et al. (2012) Exploring Topic Coherence over Many Models and Many Topics. Conference on Empirical Methods in Natural Language Processing.
Small, H. and Griffith, B.C. (1974) The Structure of Scientific Literatures. Identifying and Graphing Specialties. Science Studies, 4, 4-17. https://doi.org/10.1177/030631277400400102
Persson, O. (1994) The Intellectural Base and Research Fronts of JASIS 1986-1990. Journal of the American Society for Information Science, 45, 31-38. https://doi.org/10.1002/(SICI)1097-4571(199401)45:1 <31::AID-ASI4>3.0.CO;2-G
Zhang, S.S. (2016) A Comparative Study of Measurement Methods and Indicators of Scientific Frontier Features. Ph.D. Thesis, Dalian University of Technology, Dalian.
Feng, J. and Zhang, Y.Q. (2017) Research on Scientific Frontier Identification and Analysis Methods Based on LDA and Ontology. Information Theory and Practice, 40, 49-54. https://doi.org/10.16353/j.cnki.1000-7490.2017.08.009