Project Abstract

Human values play a rather significant role in how humans reason and act in different situations. While these concepts are rather abstract, we can explore whether they are consistently applied across various scenarios. In this research, we will exercise rule-based, machine learning, or generative AI approaches on a corpus of situational judgment questions and answers that involve these human values, in order to address the question “Can a model accurately infer and predict the ‘operative’ human value in a situation?”.By analyzing vast datasets and identifying patterns in response choices, we hope to develop a model that can not only predict the dominant value at play, but also offer insights into the relative weight and interaction of multiple values influencing a person’s decision-making process. We will place a special emphasis on the role of Situational Judgement Tests in highly sensitive areas such as the field of healthcare and investigate whether learning models can accurately predict human values in such nuanced real-world situations.

Keywords: Software Engineering, Human values,

 Conference Details

Session: Presentation Stream 8 at Presentation Slot 8

Location: GH037 at Tuesday 7th 13:30 – 17:00

Markers: Galileo Sator (GTA), Ulrich Berger

Course: MSc Computer Science, Masters PG

Future Plans: I’m looking for work