"MLMC: Visualizing Multi-Label Classification. A Tool for Intuitively Evaluating and Comparing Classifiers at Global, Label and Instance Levels"Torsten MöllerMachine learning classifiers are increasingly applied to complex tasks such as audio tagging, image labeling, and text classification -- many of which require multi-label classification. Traditional evaluation tools, often limited to single metrics like accuracy, fall short in providing insight into classifier behavior across multiple labels. To address this, we present MLMC, an interactive visualization tool designed for multi-label classifier evaluation and comparison. Based on expert interviews, MLMC supports analysis across instance-, label-, and classifier-level views, offering a scalable and more interpretable alternative. We demonstrate its use across three different domains and describe its core algorithms and user interface. Two pilot studies (N=$6$ each) provided insight into MLMC's usability and showed improved task accuracy, consistency, and user confidence compared to confusion matrices. Results highlight MLMC's potential as a practical tool for intuitive evaluation of multi-label classifiers, with implications for a broad range of machine learning applications. |
« back