Multilingual Detection of Personal Employment Status on Twitter

TL;DR

This paper explores active learning strategies to improve the detection of personal employment disclosures on Twitter across multiple languages, demonstrating significant gains in accuracy with minimal labeled data.

Contribution

It evaluates three active learning methods for multilingual employment status detection, showing their effectiveness in extreme class imbalance scenarios using BERT models.

Findings

Active learning improves precision and recall significantly.

Few iterations of active learning yield substantial performance gains.

No single active learning strategy is universally best.

Abstract

Detecting disclosures of individuals' employment status on social media can provide valuable information to match job seekers with suitable vacancies, offer social protection, or measure labor market flows. However, identifying such personal disclosures is a challenging task due to their rarity in a sea of social media content and the variety of linguistic forms used to describe them. Here, we examine three Active Learning (AL) strategies in real-world settings of extreme class imbalance, and identify five types of disclosures about individuals' employment status (e.g. job loss) in three languages using BERT-based classification models. Our findings show that, even under extreme imbalance settings, a small number of AL iterations is sufficient to obtain large and significant gains in precision, recall, and diversity of results compared to a supervised baseline with the same number of labels. We also find that no AL strategy consistently outperforms the rest. Qualitative analysis suggests that AL helps focus the attention mechanism of BERT on core terms and adjust the boundaries of semantic expansion, highlighting the importance of interpretable models to provide greater control and visibility into this dynamic learning process.