A Statistical Approach to Classification: A guide to hierarchical cluster analysis in agricultural communications research

Abstract

Classification, the sorting of similar objects or organisms into groups based on shared qualities and characteristics, is how we make sense of the world. As the field of agricultural communication and our understanding of media effects becomes more complex, it is important to have approaches that allow for a valid and reliable method of classifying units of analysis — whether they are texts, people, or other artifacts — into groups based on theoretically sound variables. This paper discusses one method of classification, the hierarchical cluster analysis, and how this method may be applied by 1) Developing Variables for Study, 2) Choosing a Sample, 3) Removing Unnecessary Variables, 4) Running the analysis, and 5) Interpreting Clusters. This professional development paper suggests this method could have positive implications for agricultural and science communication research including increased validity and reliability, rigorous development, and deeper understanding of mass communication theory. In addition, we provide recommendations for future research such as audience segmentation in agricultural and science communication research.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 16 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.