Feeling Anxious? Perceiving Anxiety in Tweets using Machine Learning

TL;DR

This paper introduces a machine learning-based tool to measure perceived anxiety from tweets, revealing how anxiety fluctuates over time and relates inversely to social engagement and popularity.

Contribution

It presents a novel non-intrusive method to quantify perceived anxiety in social media posts using machine learning, capturing longitudinal fluctuations and trait levels.

Findings

Machine learning accurately depicts anxiety fluctuations over time.

Perceived anxiety inversely correlates with social engagement.

The approach offers insights into societal and individual anxiety patterns.

Abstract

This study provides a predictive measurement tool to examine perceived anxiety from a longitudinal perspective, using a non-intrusive machine learning approach to scale human rating of anxiety in microblogs. Results suggest that our chosen machine learning approach depicts perceived user state-anxiety fluctuations over time, as well as mean trait anxiety. We further find a reverse relationship between perceived anxiety and outcomes such as social engagement and popularity. Implications on the individual, organizational, and societal levels are discussed.