User:Metcalm/sandbox

IDEA NETWORKING

Idea Networking is an inductive classification method which clusters numerous statements into a handful of categories (1). These statements might be source from interviews, text, web sites, focus groups, SWOT analysis or community consultation. It is inductive as it does not assume any prior classification system to cluster the statements. Rather keywords or issues in the statements when clustered and named provide the emergent meta themes, frames or concepts.

METHOD

List and reference number between 60 and 200 statements
Draft a table showing which statements (by reference number) are linked (paired) and why. For example statement 1 maybe linked to statements 4, 23, 45, 67, 89 and 107 because they all are about the weather (see table).

Statement	Is Linked To	Because They Are About
1	4, 23, 45, 67, 89, 107	Weather
2	16, , 29, 46, 81	Light
3	23, 45, 67, 89, 107	Interaction
4	13, 16, 34, 78, 81	Weather
Etc	Etc	Etc

Try to have between 1 and 7 links per statement; many more will result in a congested network diagram. This means choosing why the statements are linked may need grading (bad weather, good weather, wet weather etc…). This linking is sometimes called ’coding’ in thematic analysis which highlights that the statements can be linked for several reasons (source, context, time, etc). There maybe many tens of reasons why statements are linked. The same statements may be linked for different reasons. Try not to restrict the number of reasons to low number as so anticipate the resultant clustering.
Enter the reference numbers into network diagramming software, usually in the form of a matrix with the reference numbers along the top and side of the matrix. Each cell with then have a 1 or 0 to indicate whether its row and column reference number are linked.
Instruct the software to draft the network diagram using maximum node repulsion. This encourages cluster formation.
Identify about five clusters in the network diagram. Do this both visually and using the cluster identification algorithms supplied with the software (e.g. Newnan Girvan sub-groups)
Look at the statements contained within each cluster and imagine a descriptive collective adjective name for each cluster of statements (a meta narrative, classification name or label).
Report the list of statements as being clustered into your five or so cluster names (themes, frames, concepts). For example, you might report that your analysis of the statements shows that those at community meeting were using the concepts of exposure, interaction, safety, light and inspiration in their responses.

Idea Network (Note Clusters)

UNDERLYING PHILOSOPHY

In his book Synthesis of Form, the pragmatist Christopher Alexander (2)suggested networking the ideas of clients as means to identifying the major facets of a architectural design. This is still used modern design work usually using cluster analysis. Modern social networking analysis software provides a useful alternative. Computers, power stations, and people can be linked together usefully (3). These links can be represented in a matrix or network. Modern network diagramming software, with node repulsion algorithms, allows visual representation of these networks. This often reveals clusters of nodes. The same networking can be undertaken with statements, peoples’ ideas in written form. The statements become the nodes and the links are provided by an analyst linking those statements thought to be similar. Keywords, synonyms, experience or context might be used to provide this linking. For example, the statements (1) That war is economics progressed by other means, might be considered linked to the statement (2) That progress unfortunately needs the innovation which is a consequence of human conflict. In pragmatism (4), we use our conceptions to interpret our perceptions (sensory inputs). These conceptions might be represented by words as conceptual ideas or concepts. For example, if we use the conceptual idea or concepts of justice to interpret the actions of people, we get a different interpretation (or meaning) compared to using the conceptual idea of personal power. Using the conceptual idea of justice makes certain action ideas seem reasonable. These may include due process, legal representation, hearing both sides, have norms or regulations for comparison. Therefore there is a relationship between conceptual ideas and related apparently rational action ideas. If the statements gathered at a consultative meeting are considered action ideas, then clusters of these similar actions ideas might be considered to examples of a meta idea or conceptual idea. These are also called themes, and frames. Modern research extending Miller’s Magic number7 plus or minus 2, to idea handling, suggests a five part classification is appropriate for humans (5). Using networking to cluster statements is considered advantageous because:

It provides a multi-dimensional alternative to sticking up post-it notes in clusters.
It offers a convenient graphic which can be presented in reports and analysed using network metrics
It is an auditable process where each step taken can be explained in supporting documentation.
It is a qualitative alternative, and thus more subtle and transparent, than cluster analysis, factor analysis, multidimensional scaling or principle components. This subtleness includes enabling the analyst to deal with metaphor, synonyms, pronouns and alternative terminology generally. No variables (variation in numerical data) are necessary.

SOFTWARE

Any networking software with node repulsion (spring embeddedness) is suitable. UCINET6 (6) has an old interface but reliable underlying mathematics. It runs on Microsoft only, costing less than $100. NodeXL (7) is an Excel add-on so has an Excel type interface, is Open Source and free, and has some very good graphics, including curved links. The data entry into columns rather that a matrix is long winded but the paste and copy facility in Excel useful.

ALSO SEE

REFERENCES

Metcalfe, M. 2007. Problem Conceptualisation Using Idea Networks. Systemic Practice and Action Research 20(2) 141-150.
Alexander, C. 1964. Notes On The Synthesis Of Form. Harvard University Press, Mass.
Inkpen, A.C., E.W.K. Tsang. 2005. Social Capital, Networks, And Knowledge Transfer. Academy Of Management Review 30(1) 146-165.
Rorty, R. 1982. Consequences of Pragmatism. University of Minnesota Press, Minneapolis.
Miller, G.A. 1956. The Magical Number Seven, Plus or Minus Two: Some Limits on Our Capacity for Processing Information. The Psychological Review vol. 63 pp. 81-97.
Borgatti, S.P., M. Everett, L.C. Freeman. 2002. Ucinet for Windows: software for social network analysis. Analytic Technologies, Harvard, MA http://www.analytictech.com/ucinet/
NodeXL http://nodexl.codeplex.com/