Kerne, A., Smith, S.M., Webb, A., Linder, Lupfer, N., Qu, Y., R., Moeller, J., Damaraju, S.,Information-based Ideation Metrics show that Mixed-Initiative Information Composition Provokes Creativity, ACM Transactions on Computer-Human Interaction (ToCHI), 21(3), June 2014, 48 pages.
This week I write a article about information based ideation metrics. The technology introduce a kind of method, which are used to evaluate the creativity of the products people made.
At first, this article introduce a term IBI-information based ideation-used for investigating the open-end tasks and activities in which users develop new ideas. Curation is kind of activity that combines conceptualization, finding, choosing information objects, annotation and synthesis. Ideation means new idea.
Ideation could be measured in four parts: Fluency is the number of ideas, Flexibility/Variety addresses the investigation of alternative interpretations, Novelty is the rareness of an idea and Quality addresses more contextual features of creative products.
After we get the training data sets, we can do evaluation. The evaluation methods include the Elemental Ideation Metrics of Curation and Holistic Ideation Metrics of Curation. There are huge bound of equations to evaluate creativity in four parts we mentioned above.
As for holistic ideation metrics of curation, we have criteria for the assessment of each holistic metric. That is-Emergence, Relevance, Visual Presentation and Exposition/Written Presentation.
Another important method is statistical method for testing the creativity. It includes Comparing Ideation Metric Distributions Across Conditions, Comparing Ideation Metric Distributions Across Raters: Inter-rater Reliability and Multiple Comparisons.
Then the article gives a case and analysis it. It suggests the challenge we will face when doing creative tasks.
And MI2C in the article is another important term. It refers to MIXED-INITIATIVE INFORMATION COMPOSITION. It used to give user space, valued-add information, timing services based on user attention, mining the cost of poor guesses, efficient urgent, dialogue to refine results, uncertainty about user goals and working memory of recent action.
It is really useful in our final project to evaluate our design and improve it.