Trend Analysis of Machine Learning Research Using Topic Network Analysis

In this paper, a topic network analysis approach is proposed which integrates topic modeling and social network analysis. We collected 16,855 scientific papers from six top journals in the field of machine learning published from 1997 to 2016 and analyzed them with the topic network. The dataset is break down into 4 intervals to identify topic trends and performed the time-series analysis of topic network. Our experimental results show centralization of the topic network has the highest score from 2002 to 2006, and decreases for next 5 years and increases again. For last 5 years, centralization of the degree centrality and closeness centrality increases, while centralization of the betweenness centrality decreases again. Also, data analytic and computer vision are identified as the most interrelated topic among other topics. Topics with the highest degree centrality evolve component analysis, text mining, biometric and computer vision according to time. Our approach extracts the interrelationships of topics, which cannot be detected with conventional topic modeling approaches, and provides topical trends of machine learning research.