# Stopping Active Learning based on Predicted Change of F Measure for Text Classification

## TL;DR

This paper introduces a new stopping method for active learning in text classification that estimates model performance change to reduce annotation costs, applicable with any base learner.

## Contribution

The paper proposes the Predicted Change of F Measure method, a novel approach to determine when to stop active learning based on predicted performance change.

## Key findings

- Effective in reducing annotation effort
- Applicable with any base learner
- Provides reliable performance change estimates

## Abstract

During active learning, an effective stopping method allows users to limit the number of annotations, which is cost effective. In this paper, a new stopping method called Predicted Change of F Measure will be introduced that attempts to provide the users an estimate of how much performance of the model is changing at each iteration. This stopping method can be applied with any base learner. This method is useful for reducing the data annotation bottleneck encountered when building text classification systems.