Abstract:Social agents and robots are increasingly being used in wellbeing settings. However, a key challenge is that these agents and robots typically rely on machine learning (ML) algorithms to detect and analyse an individual's mental wellbeing. The problem of bias and fairness in ML algorithms is becoming an increasingly greater source of concern. In concurrence, existing literature has also indicated that mental health conditions can manifest differently across genders and cultures. We hypothesise that the representation of features (acoustic, textual, and visual) and their inter-modal relations would vary among subjects from different cultures and genders, thus impacting the performance and fairness of various ML models. We present the very first evaluation of multimodal gender fairness in depression manifestation by undertaking a study on two different datasets from the USA and China. We undertake thorough statistical and ML experimentation and repeat the experiments for several different algorithms to ensure that the results are not algorithm-dependent. Our findings indicate that though there are differences between both datasets, it is not conclusive whether this is due to the difference in depression manifestation as hypothesised or other external factors such as differences in data collection methodology. Our findings further motivate a call for a more consistent and culturally aware data collection process in order to address the problem of ML bias in depression detection and to promote the development of fairer agents and robots for wellbeing.
Abstract:Recent studies show bias in many machine learning models for depression detection, but bias in LLMs for this task remains unexplored. This work presents the first attempt to investigate the degree of gender bias present in existing LLMs (ChatGPT, LLaMA 2, and Bard) using both quantitative and qualitative approaches. From our quantitative evaluation, we found that ChatGPT performs the best across various performance metrics and LLaMA 2 outperforms other LLMs in terms of group fairness metrics. As qualitative fairness evaluation remains an open research question we propose several strategies (e.g., word count, thematic analysis) to investigate whether and how a qualitative evaluation can provide valuable insights for bias analysis beyond what is possible with quantitative evaluation. We found that ChatGPT consistently provides a more comprehensive, well-reasoned explanation for its prediction compared to LLaMA 2. We have also identified several themes adopted by LLMs to qualitatively evaluate gender fairness. We hope our results can be used as a stepping stone towards future attempts at improving qualitative evaluation of fairness for LLMs especially for high-stakes tasks such as depression detection.
Abstract:Unfair predictions of machine learning (ML) models impede their broad acceptance in real-world settings. Tackling this arduous challenge first necessitates defining what it means for an ML model to be fair. This has been addressed by the ML community with various measures of fairness that depend on the prediction outcomes of the ML models, either at the group level or the individual level. These fairness measures are limited in that they utilize point predictions, neglecting their variances, or uncertainties, making them susceptible to noise, missingness and shifts in data. In this paper, we first show that an ML model may appear to be fair with existing point-based fairness measures but biased against a demographic group in terms of prediction uncertainties. Then, we introduce new fairness measures based on different types of uncertainties, namely, aleatoric uncertainty and epistemic uncertainty. We demonstrate on many datasets that (i) our uncertainty-based measures are complementary to existing measures of fairness, and (ii) they provide more insights about the underlying issues leading to bias.