# Multimodal Classification of Urban Micro-Events

## TL;DR

This paper investigates methods for detecting small-scale urban micro-events using multimodal citizen sensing data, demonstrating that hybrid fusion approaches improve classification accuracy over unimodal methods.

## Contribution

It introduces and evaluates hybrid fusion techniques and multimodal graph embeddings for classifying urban micro-events, showing their effectiveness over traditional unimodal approaches.

## Key findings

- Hybrid fusion with multimodal embeddings performs best.
- Multimodal approaches outperform unimodal classifiers.
- Real-world data confirms improved micro-event detection accuracy.

## Abstract

In this paper we seek methods to effectively detect urban micro-events. Urban micro-events are events which occur in cities, have limited geographical coverage and typically affect only a small group of citizens. Because of their scale these are difficult to identify in most data sources. However, by using citizen sensing to gather data, detecting them becomes feasible. The data gathered by citizen sensing is often multimodal and, as a consequence, the information required to detect urban micro-events is distributed over multiple modalities. This makes it essential to have a classifier capable of combining them. In this paper we explore several methods of creating such a classifier, including early, late, hybrid fusion and representation learning using multimodal graphs. We evaluate performance on a real world dataset obtained from a live citizen reporting system. We show that a multimodal approach yields higher performance than unimodal alternatives. Furthermore, we demonstrate that our hybrid combination of early and late fusion with multimodal embeddings performs best in classification of urban micro-events.