Topic-time Heatmaps for Human-in-the-loop Topic Detection and Tracking

TL;DR

This paper introduces a human-in-the-loop approach using topic-time heatmaps to iteratively refine topic detection and tracking, aiding users in better understanding and defining event scopes in news corpora.

Contribution

It proposes a visual, interactive method that combines heatmaps and user feedback to improve event detection accuracy and interpretability.

Findings

Enhanced user understanding of event structures

Improved accuracy of event clustering

Effective iterative refinement process

Abstract

The essential task of Topic Detection and Tracking (TDT) is to organize a collection of news media into clusters of stories that pertain to the same real-world event. To apply TDT models to practical applications such as search engines and discovery tools, human guidance is needed to pin down the scope of an "event" for the corpus of interest. In this work in progress, we explore a human-in-the-loop method that helps users iteratively fine-tune TDT algorithms so that both the algorithms and the users themselves better understand the nature of the events. We generate a visual overview of the entire corpus, allowing the user to select regions of interest from the overview, and then ask a series of questions to affirm (or reject) that the selected documents belong to the same event. The answers to these questions supplement the training data for the event similarity model that underlies the system.