r-Instance Learning for Missing People Tweets Identification

TL;DR

This paper introduces an r-instance learning model leveraging social media data to improve the identification of missing people, addressing the challenge of heterogeneous information fusion in social media analysis.

Contribution

It proposes a novel r-instance learning approach inspired by homophily theory to better integrate diverse social media data for missing people identification.

Findings

Enhanced accuracy in missing people detection.

Effective fusion of heterogeneous social media data.

Improved social resource allocation for search efforts.

Abstract

The number of missing people (i.e., people who get lost) greatly increases in recent years. It is a serious worldwide problem, and finding the missing people consumes a large amount of social resources. In tracking and finding these missing people, timely data gathering and analysis actually play an important role. With the development of social media, information about missing people can get propagated through the web very quickly, which provides a promising way to solve the problem. The information in online social media is usually of heterogeneous categories, involving both complex social interactions and textual data of diverse structures. Effective fusion of these different types of information for addressing the missing people identification problem can be a great challenge. Motivated by the multi-instance learning problem and existing social science theory of "homophily", in this paper, we propose a novel r-instance (RI) learning model.