Explaining Differences in Classes of Discrete Sequences
It addresses the need for increased explainability in human behavior research, such as psychology, where understanding differences is prioritized over prediction accuracy.
The paper tackles the problem of explaining differences between classes of discrete sequences, which existing classification and clustering methods fail to do, by introducing techniques like k-gram silhouette scores and subsequence distance analysis to interpret black-box models, applied in case studies on GitHub teams and Minecraft events.
While there are many machine learning methods to classify and cluster sequences, they fail to explain what are the differences in groups of sequences that make them distinguishable. Although in some cases having a black box model is sufficient, there is a need for increased explainability in research areas focused on human behaviors. For example, psychologists are less interested in having a model that predicts human behavior with high accuracy and more concerned with identifying differences between actions that lead to divergent human behavior. This paper presents techniques for understanding differences between classes of discrete sequences. Approaches introduced in this paper can be utilized to interpret black box machine learning models on sequences. The first approach compares k-gram representations of sequences using the silhouette score. The second method characterizes differences by analyzing the distance matrix of subsequences. As a case study, we trained black box supervised learning methods to classify sequences of GitHub teams and then utilized our sequence analysis techniques to measure and characterize differences between event sequences of teams with bots and teams without bots. In our second case study, we classified Minecraft event sequences to infer their high-level actions and analyzed differences between low-level event sequences of actions.