Detecting Dynamics of Hot Topics with Alluvial Diagrams: A Timeline Visualization

Purpose In this paper, we combined the method of co-word analysis and alluvial diagram to detect hot topics and illustrate their dynamics. Design/methodology/approach Articles in the field of scientometrics were chosen as research cases in this study. A time-sliced co-word network was generated and then clustered. Afterwards, we generated an alluvial diagram to show dynamic changes of hot topics, including their merges and splits over time. Findings After analyzing the dynamic changes in the field of scientometrics from 2011 to 2015, we found that two clusters being merged did not mean that the old topics had disappeared and a totally new one had emerged. The topics were possibly still active the following year, but the newer topics had drawn more attention. The changes of hot topics reflected the shift in researchers’ interests. Research topics in scientometrics were constantly subdivided and re-merged. For example, a cluster involving “industry” was divided into several topics as research progressed. Research limitations When examining longer time periods, we encounter the problem of dealing with bigger data sets. Analyzing data year by year would be tedious, but if we combine, e.g. two years into one time slice, important details would be missed. Practical implications This method can be applied to any research field to illustrate the dynamics of hot topics. It can indicate the promising directions for researchers and provide guidance to decision makers. Originality/value The use of alluvial diagrams is a distinctive and meaningful approach to detecting hot topics and especially to illustrating their dynamics.