This paper uses data mining and artificial intelligence on the metadata's literature for the past 20 years. Authors compared about 2700 papers and classified them into 20 topics based on the words included in the paper's topic and abstract. Then, the paper discusses those topics in detail. For instance, each topic's timeline and explain the factors that affect increasing or decreasing the number of research topics. Also, they support their claims with graphs generated by R. These visualizations make the paper much understandable and give a clear vision of what the writers want to say.
In my opinion, using neural network, k-means, and other techniques on the generated topics to understand the relationship between these topics makes the article more attractive. Merging the theoretical part with the technical part to find the relationships create new critical questions, which allow the author to explain and answer these questions cames from these insights.
This paper gave me a new type of research that can be done. Analyzing the articles and papers about a topic can provide new insights to understand it from academic aspects. Knowing the trend in any topic through time will give opportunities to understand the topic needs, which gives the researchers an idea to contribute and enrich that topic with the proper portions of research.
This article, in my belief, is organized and well written. The titles, sequencing, and sup-titles are logical, and the paper's language is clear and not so complicated. After reading this paper, I wish if the writers not stop with 20 topics. If they expand the topic number, they may find new insights from the new relationships generated from the additional topics. In addition, in fig.5, they abandoned the topics that have no connection with others. I think it is better to include them and discuss why they have no relation with the other topics.
Zaid Altukhi
Oh, J. S., & Park, O. N. (2018). Topics and Trends in Metadata Research. Journal of Information Science Theory and Practice, 6(4), 39–53. https://doi.org/10.1633/JISTaP.2018.6.4.4