Visual Analysis of Tobacco Leaf Recognition Research Based on CiteSpace

This study utilizes CiteSpace software to conduct a visual analysis of the literature in the field of tobacco leaf recognition technology in recent years, aiming to reveal the research hotspots, development trends, and contributions of key institutions and scholars in this domain. By analyzing the changes in the number of publications, keyword co-occurrence networks, author collaboration patterns, and keyword burst situations, this paper demonstrates the in-depth exploration and innovation in both basic research and practical applications of tobacco leaf recognition technology. Firstly, through the analysis of the annual publication volume, we found that research on tobacco leaf recognition has shown a significant growth trend over the past decade, indicating the increasing importance of this field in both academia and industrial applications. Secondly, the analysis of research institutions and authors reveals the dominant positions of institutions such as the Chinese Academy of Agricultural Sciences, the Chinese Academy of Sciences, and N anjing Agricultural University, as well as the outstanding contributions of scholars like Wang Ying, Wang Lu, and Guo Yongfeng in terms of publication volume and collaboration relationships. Furthermore, the keyword co-occurrence network and cluster analysis show that the research focus of tobacco leaf recognition technology covers multiple keyword groups, including gene expression, transcription factors, plant resistance, and biosynthesis, reflecting researchers' multifaceted efforts in theoretical exploration and practical applications. Finally, the keyword burst analysis reveals the rise and fall of keywords in different periods. For instance, the period from 2014 to 2017 was mainly concentrated on “gene expression” and “transgenic tobacco,” while from 2018 to 2020, emerging research hotspots such as “functional analysis” and “cell death” became prominent. This study provides profound insights and significant references for the future development of tobacco leaf recognition technology, offering theoretical and practical guidance for its application in the tobacco industry by academia and industry.