Capturing Emotional Reactions to Data Visualization
Background
Data visualizations, especially those with interactive components, are a recent hot topic in the intersection of tech and journalism. They are an engaging way of presenting volumes of information but incur challenges related to the assessment of the effectiveness of these visualizations. State-of-the-art technologies that can use live video footage to capture and analyze people’s emotional responses are one way of deciphering reactions to data visualizations. However, technical and design challenges will still need to be addressed with respect to linking interactive visualizations with emotion-capture technologies, keeping records of real-time emotional states, and graphically rendering people’s interactions with these visualizations to shed light on how they can improve.
Executive Summary
Sets of visualizations already exist and are plentiful on news organization websites, for example. The primary task is in developing a general tool that can extract emotional state/interaction data from any person’s experience with a visualization. We would need to look into pre-existing libraries that integrate with webcams to analyze and detect changes in emotional state in real-time. It may be helpful to construct a platform that amasses “emotional profiles” of users and detects patterns or irregularity in their use of a range of visualizations and stimuli. Stripping identifying information from these profiles as well as encrypting logs is essential when implementing this platform. To ensure the accuracy of the computed emotional reactions, a post-quiz should be given to participants who can indirectly validate or invalidate the results based on their own perceptions of levels of confusion, fascination, or interest in the visualizations they were presented with.
Viability Analysis
Finding open-source or non-licensed libraries for emotion-capturing webcam software may be difficult, depending on technology patents. Deciding the best way to represent extensive logs of emotional states in aggregate will require some research insofar as choosing a best visualization as well as safeguarding the privacy of participants. Consistency in factors such as background lighting and webcam quality may prove to be very important, so it may be best to administer the interactions in a controlled environment on Bucknell computers where we can control as many variables as possible — but this may become challenging if the client hopes to make use of the tool by recruiting participants around the world (on Amazon’s Mechanical Turk, for instance).
Risks and Rewards
Risks include privacy violations in light of IRB restrictions as well as falsely representing the emotional reactions of participants which could go on to influence decisions of data visualization creators and designers. Rewards include potential to interact with visualizations in new ways by garnering a better understanding of what works and what doesn’t across demographic categories and different people. Such improvements to data visualizations as a result of the feedback provided by this tool will positively impact active learning and engagement with an array of data, ranging from politics to science or any sort of quantitative observation.
Closing
The development of this system will be an instrumental stepping stone if we hope to continue disseminating information effectively and pragmatically on the web. A voluntary or crowdsourced platform that assesses emotional impact while protecting the privacy of its users has enormous potential to positively reinforce quality visualizations and critique poor visualizations, to the effect of creating and encouraging better, more informational online resources.
Print 
PDF