Classification-Aware Neural Topic Model Combined With Interpretable Analysis -- For Conflict Classification

TL;DR

This paper introduces CANTM-IA, a neural topic model designed for conflict event classification that enhances interpretability and classification accuracy through integrated interpretability analysis and optimized architecture.

Contribution

The paper presents a novel neural topic model that combines classification awareness with interpretability, improving conflict classification and topic discovery.

Findings

Enhanced interpretability of conflict classification results

Improved classification accuracy over baseline models

Reduced model complexity through architecture optimization

Abstract

A large number of conflict events are affecting the world all the time. In order to analyse such conflict events effectively, this paper presents a Classification-Aware Neural Topic Model (CANTM-IA) for Conflict Information Classification and Topic Discovery. The model provides a reliable interpretation of classification results and discovered topics by introducing interpretability analysis. At the same time, interpretation is introduced into the model architecture to improve the classification performance of the model and to allow interpretation to focus further on the details of the data. Finally, the model architecture is optimised to reduce the complexity of the model.