Let the Users Compete: A Gamified Interactive Machine Learning Approach

Theoretical (Analytical):

Practical (Implementation):

Literature Work:


Overview

Due to different challenges such as the data overload or complex cognitive processes required to fulfill a Visual Analytics (VA) task, the users may lose motivation and fail to reach deeper levels of analysis. To support user motivation, one can use gamification, i.e., gameful design. Gamification is a strategy of applying game elements (e.g., a competition) in a non-game context with the goal of motivating users while performing a given task.

Problem Statement

The users may lose engagement, especially when performing repetitive tasks, i.e., when interactively creating or updating a machine learning model. The goal of the project is to implement a collaborative VA system, where users can compete with each other while improving the quality of a clustering model.

Tasks

  • Implement feature extraction techniques suitable for the analysis task.
  • Implement quality metrics to measure the generated cluster quality.
  • Develop a collaborative VA system, in which users can compete with each other while improving the quality of a clustering model.

Requirements

Good programming skills in Java and Javascript

Scope/Duration/Start

  • Scope: Master
  • 6 Month Project, 6 Month Thesis
  • Start: immediately

Contact

References

R. Sevastjanova, H. Schäfer, J. Bernard, D. A. Keim, M. El-Assady. Shall we play? – Extending the Visual Analytics Design Space through Gameful Design Concepts. Machine Learning from User Interactions for Visualization and Analytics, IEEE VIS 2019 workshop, to appear, 2019.