A Topic-Based Bibliometric Analysis of Precision Agriculture Research Using BERTopic
TL;DR
Examination of research trends related to precision agriculture through topic-based bibliometric analysis revealed temporal changes in topics, indicating that research on disease detection using deep learning has become increasingly active in recent years.
Abstract
Precision agriculture is a technological framework that applies various information and communication technologies, such as remote sensing and Internet of Things (IoT), to agriculture. In recent years, advances in artificial intelligence and robotics technologies have led to the widespread adoption of precision agriculture (i.e., smart agriculture), which is expected to improve productivity and reduce labor, making it an important technology for enhancing the sustainability of agriculture in the future. Therefore, in this study, we aimed to examine the research trends related to precision agriculture through topic-based bibliometric analysis. Additionally, we performed dynamic topic modeling to examine the evolution of research trends over time. We used BERTopic, which has become increasingly popular in recent years, as the topic modeling implementation tool. The data analyzed were the title texts of academic papers related to precision agriculture obtained from the OpenAlex academic literature database. By applying the topic modeling tool BERTopic to these title texts, we extracted a variety of topics from previous research on precision agriculture, including research on unmanned aerial vehicles (UAVs) and the IoT. Furthermore, application of the dynamic topic model revealed temporal changes in topics, indicating that research on disease detection using deep learning has become increasingly active in recent years.