How UMass-FSD Inadvertently Leverages Temporal Bias

TL;DR

This paper uncovers a temporal bias in the UMass-FSD system for First Story Detection, showing that leveraging this bias improves detection accuracy and can be intentionally incorporated into models.

Contribution

It is the first to identify and analyze the temporal bias in UMass-FSD and demonstrates how intentionally leveraging this bias enhances detection performance.

Findings

UMass-FSD's performance is partly due to temporal bias.

Leveraging temporal bias improves detection accuracy.

The bias applies to other FSD systems and can be intentionally used.

Abstract

First Story Detection describes the task of identifying new events in a stream of documents. The UMass-FSD system is known for its strong performance in First Story Detection competitions. Recently, it has been frequently used as a high accuracy baseline in research publications. We are the first to discover that UMass-FSD inadvertently leverages temporal bias. Interestingly, the discovered bias contrasts previously known biases and performs significantly better. Our analysis reveals an increased contribution of temporally distant documents, resulting from an unusual way of handling incremental term statistics. We show that this form of temporal bias is also applicable to other well-known First Story Detection systems, where it improves the detection accuracy. To provide a more generalizable conclusion and demonstrate that the observed bias is not only an artefact of a particular implementation, we present a model that intentionally leverages a bias on temporal distance. Our model significantly improves the detection effectiveness of state-of-the-art First Story Detection systems.