Scholarlink

<p>Concept Mapping (CM) is promoted as a research method suitable for interdisciplinary and international research, “… best suited to applications where diverse or wide-ranging opinions need to be gathered and made sense of.” Our study does not support this claim in practical applications when data are analyzed as prescribed by the same literature. Neither the conventional analytic approach in CM nor alternative clustering algorithms appear to be able to reveal meaningful attributes when these attributes vary between different sorters. CM may be appropriate to use when groups can be assumed to be homogeneous, but CM cannot test this assumption. Furthermore, proposed methods for data reduction obscure the discovery of meaningful attributes even when groups are homogeneous. However, we demonstrate by means of proof of principle experiments, that if the general approach to concept mapping data is mediated such that (1) steps to identify possible heterogeneity of the sorters are taken, (2) the modeling approach to attribute identification uses the full distance (or co-occurrence) matrix of statements instead of a two-dimensional reduction by multi-dimensional scaling, and (3) appropriate visualization methods of the cluster analysis are used, Concept Mapping can produce meaningful results.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

The validity of concept mapping: let’s call a spade a spade

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年9月2日

查看全文
  • Jarl K. Kampen,
  • Jos A. Hageman,
  • Marian Breuer,
  • Hilde Tobi

摘要

Concept Mapping (CM) is promoted as a research method suitable for interdisciplinary and international research, “… best suited to applications where diverse or wide-ranging opinions need to be gathered and made sense of.” Our study does not support this claim in practical applications when data are analyzed as prescribed by the same literature. Neither the conventional analytic approach in CM nor alternative clustering algorithms appear to be able to reveal meaningful attributes when these attributes vary between different sorters. CM may be appropriate to use when groups can be assumed to be homogeneous, but CM cannot test this assumption. Furthermore, proposed methods for data reduction obscure the discovery of meaningful attributes even when groups are homogeneous. However, we demonstrate by means of proof of principle experiments, that if the general approach to concept mapping data is mediated such that (1) steps to identify possible heterogeneity of the sorters are taken, (2) the modeling approach to attribute identification uses the full distance (or co-occurrence) matrix of statements instead of a two-dimensional reduction by multi-dimensional scaling, and (3) appropriate visualization methods of the cluster analysis are used, Concept Mapping can produce meaningful results.