Aspect-Based Sentiment Analysis for Open-Ended HR Survey Responses

TL;DR

This work tackles aspect-based sentiment analysis (ABSA) for Dutch open-ended HR survey responses, evaluating BERT-based few-shot learning against bag-of-words and zero-shot baselines. It introduces a two-stage ABSA pipeline (aspect identification followed by sentiment labeling), leverages clustering to identify six HR-relevant aspects, and builds a labeled dataset of 1,458 responses with domain-expert validation. The study finds that Dutch BERT models, especially RobBERT, significantly outperform baselines in few-shot ABSA, while data augmentation helps primarily for aspect classification with RobBERT; zero-shot transfer underperforms in this domain. The results support the practical utility of few-shot ABSA for HR analytics and highlight the need for larger, diverse data and alternative clustering or semi-supervised methods to improve generalization.

Abstract

Understanding preferences, opinions, and sentiment of the workforce is paramount for effective employee lifecycle management. Open-ended survey responses serve as a valuable source of information. This paper proposes a machine learning approach for aspect-based sentiment analysis (ABSA) of Dutch open-ended responses in employee satisfaction surveys. Our approach aims to overcome the inherent noise and variability in these responses, enabling a comprehensive analysis of sentiments that can support employee lifecycle management. Through response clustering we identify six key aspects (salary, schedule, contact, communication, personal attention, agreements), which we validate by domain experts. We compile a dataset of 1,458 Dutch survey responses, revealing label imbalance in aspects and sentiments. We propose few-shot approaches for ABSA based on Dutch BERT models, and compare them against bag-of-words and zero-shot baselines. Our work significantly contributes to the field of ABSA by demonstrating the first successful application of Dutch pre-trained language models to aspect-based sentiment analysis in the domain of human resources (HR).