U.S. Department of Energy

Pacific Northwest National Laboratory

Towards Enabling Complex Sensemaking from Streaming Data

Sensemaking is a cognitively demanding process and has been the focus of considerable research from varied disciplines including cognitive psychology, neuroscience, and information sciences. We bring this research into streaming environments now to learn how to support tasks beyond simple anomaly detection and situation awareness.

This project is meant to help people burdened with constantly changing data to do more complex analytic tasks like understand and predict trends.

Approach

Our approach involves modeling human tasks in streaming environments to better understand the balance of effort between human and machine. We make use of developing methods for implicit steering of such machine efforts to support deeper analytical discourse between human and analytic environment. Task analysis will also provide classification methods which can inform what types of machine support will be most beneficial at each stage of the analytic process.

The combination of these approaches will create a more complete and robust model of sensemaking that will truly capture what it means to do complicated analytic tasks in a streaming context.

Benefit

Our goal is to help people make better use of their data by understanding:

  • How much information they can handle at once
  • What ways are simplest for them to interact with or manipulate their data
  • How constantly changing information affects analytical reasoning

When we understand this process, we will be able to increase the complexity of human-in-the-loop analytic tasks performed in streaming data environments.

| Pacific Northwest National Laboratory