UX on data science visualization – MindProber vision
Andreia Ribeiro | October 16, 2018
The first section and the most complex of MindProber dashboard is ‘Time Analysis’ – where, in a second-by-second basis, the client can observe the performance of the media content and the moments with higher vs. low impact.
This section was particularly challenging due to the high volume of information to be displayed – biometric data and declarative data are provided from a general perspective to a detailed analysis. Thus, various interactivity patterns were applied, such as zooming (which allows the user to see the data in detail over a given period of time) and filters (to show different segments). The graphs are interconnected and when you make a change in the time window or segments under analysis, all graphs will be modified according to those changes.
Due to the large amount of information to be presented, we consider the division of the viewing area in ‘Biometrics’ graph’, ‘Like and Dislike graph’, ‘Affective Space graph’ and Video.
This graphic represents the timeline of the content showing the evolution of emotional activation. This data is complemented by the “margin of error” and “highlights” (optionally visible). The margin of error represents the similarity of responses among panelists. The lowest the margin, the greater the degree of similarity among panelist’s responses. This measurement is represented by a shaded area around the line. Highlights are only available when there is some selected targeting variable and indicate great discrepancies between panelist segments.
2.Did you Like or Dislike?
The declarative analysis could be continuous or discreet. The continuous analysis is represented by a time series (with the same functionalities as the biometric graph’s). There are two dimensions – the y-axis refers to an average response per second, ranging from 0 to 100, where 0 means to hate and 100 means to love a certain instant of the content and the x-axis refers to the length of the content (in seconds). The discreet analysis is represented by a stacked bar graph of two dimensions: time (xx) and frequency of response (per panelists) (yy). In the frequency of response, the positive side represents a positive response (likes) and the negative side represents the negative response (dislikes). In this graph the user can also choose to visualize declarative responses as a density function (total of positive and negative responses per second) and the valence (average of responses per second).
This graph has two dimensions: y-axis refers to arousal (biometric data) and the x-axis corresponds to valence (declarative data). This representation serves to locate each second-wise sample (represented by a circle) in a quadrant of the affective space and thus, to identify the average emotional state of the panelists in respect to the content under analysis.
On the next post, the design of MindProber Platform will be discussed so, stay in touch.
You may also like…
The potential in James One
James One was designed and released to be used by panelists. It has been doing great for the last 8 months having acquired biometric data in thousands of study participations. It measures heart rate – the number of times your heart beats per minute – an important index in the study of emotions. In addition, […]
Performance in data visualization
The MindProber Reporting tool has multiple visualization options regarding the data collected during the study. The most problematic section in terms of performance was the Timeline Analysis, and that’s what we will cover on this post, what were the problems and how we manage to solve them. Performance is crucial in order to create a […]
Scripted deployments in Elastic Beanstalk
With the advent of cloud computing services, hosting and managing a platform has never been easier. Nowadays, aspects like servers, networking, storage, and virtualization are handled by a provider who rents a piece of their infrastructure (huge data centers, scattered around the world). They also offer several tools to manage them, lifting the burden of […]