Research Constituents and Trends in Smart Farming: An Analytical Retrospection from the Lens of Text Mining

Abstract

Agriculture research began with the idea that local systems are interconnected. Thus, it was crucial to consider farmers, crops, and livestock. Smart farming arose with the Internet of Things (IoT) as people progressively digitized farming with new information technology. Academic and scientific groups innovate and commercialize IoT-based agricultural products and solutions. Many public and private organizations also explore farming advancements. Therefore, we must stimulate communication and cooperation among the many farming industry actors to build smart agricultural standards and improve system and technology interoperability. The study analyzed 3,229 published articles from smart farming systems in the Scopus database between 2008 and 2022. The collected corpus is preprocessed through various steps, creating a bag of words. Text mining, latent semantic analysis, and network analysis are applied to the collected corpus to provide current research areas based on the key terms. The key terms are taken based on the term frequency-inverse document frequency score. The research was experimented with using KNIME and VOSviewer. Finally, 10 current research areas are provided using K-means clustering for a future researcher for deep insight. This study offered years of analysis, top journals, top authors, and leading countries contributing to smart farming. Research into the myriad issues facing smart farming could begin with these trends. This research helps future researchers understand smart farming and areas that need more attention. It also draws attention to research directions that could use further study.

Intellectual Structure of Explainable Artificial Intelligence: a Bibliometric Reference to Research Constituents

“…Scopus was chosen because it provides more information than other databases like the Web of Science [33]. The initial search in both databases supported this, with Scopus providing more relevant documents than the Web of Science [34]. The proposed methodology used in this study is represented in Fig.…”

Machine Learning Techniques for Coffee Classification: A Comprehensive Review of Scientific Research

“…The study of [9] analyzes technologies for detecting roast-level coffee beans, but not all studies use ML techniques. Many studies related to smart agriculture [10,11] address machine learning techniques for classifications of other types of crops, such as rice [12][13][14][15], corn [16,17] and soybean [18]. A Comprehensive Review was used to achieve the proposed objective of synthesizing and understanding how ML techniques for coffee classification are presented in scientific research.…”