An Effectiveness Metric for Ordinal Classification: Formal Properties and Experimental Results

TL;DR

This paper introduces a new metric for ordinal classification that effectively captures class ordering information, grounded in Measurement and Information Theory, and demonstrates its advantages through theoretical analysis and experiments.

Contribution

It proposes the Closeness Evaluation Measure, a novel metric that unifies and generalizes existing evaluation metrics for ordinal classification tasks.

Findings

The new metric captures quality aspects from multiple traditional metrics.

It generalizes popular nominal and interval scale metrics.

Experimental results validate its effectiveness on synthetic and real data.

Abstract

In Ordinal Classification tasks, items have to be assigned to classes that have a relative ordering, such as positive, neutral, negative in sentiment analysis. Remarkably, the most popular evaluation metrics for ordinal classification tasks either ignore relevant information (for instance, precision/recall on each of the classes ignores their relative ordering) or assume additional information (for instance, Mean Average Error assumes absolute distances between classes). In this paper we propose a new metric for Ordinal Classification, Closeness Evaluation Measure, that is rooted on Measurement Theory and Information Theory. Our theoretical analysis and experimental results over both synthetic data and data from NLP shared tasks indicate that the proposed metric captures quality aspects from different traditional tasks simultaneously. In addition, it generalizes some popular classification (nominal scale) and error minimization (interval scale) metrics, depending on the measurement scale in which it is instantiated.