Media / Publication
October 25, 2025

Taking a SEAT: Predicting Value Interpretations from Sentiment, Emotion, Argument, and Topic Annotations

This study tests whether language models can better predict how individuals interpret human values by learning from their prior annotation behaviour, rather than relying only on demographic characteristics. Providing examples across sentiment, emotion, argument, and topic annotations improved predictions, highlighting the value of designing AI systems that account for diverse individual perspectives.

Abstract

Our interpretation of value concepts is shaped by our sociocultural background and lived experiences, and is thus subjective. Recognizing individual value interpretations is important for developing AI systems that can align with diverse human perspectives and avoid bias toward majority viewpoints. To this end, we investigate whether a language model can predict individual value interpretations by leveraging multi-dimensional subjective annotations as a proxy for their interpretive lens. That is, we evaluate whether providing examples of how an individual annotates Sentiment, Emotion, Argument, and Topics (SEAT dimensions) helps a language model in predicting their value interpretations. Our experiment across different zero- and few-shot settings demonstrates that providing all SEAT dimensions simultaneously yields superior performance compared to individual dimensions and a baseline where no information about the individual is provided. Furthermore, individual variations across annotators highlight the importance of accounting for the incorporation of individual subjective annotators. To the best of our knowledge, this controlled setting, although small in size, is the first attempt to go beyond demographics and investigate the impact of annotation behavior on value prediction, providing a solid foundation for future large-scale validation.

To continue reading please visit: https://doi.org/10.48550/arXiv.2510.01976

This open access article was presented at the Third International Workshop on Value Engineering in AI (VALE 2025) on 25 October 2025.

Dobrinoiu, A. N., Marcu, A. C., Homayounirad, A., Siebert, L. C., & Liscio, E. (2025). Taking a SEAT: Predicting Value Interpretations from Sentiment, Emotion, Argument, and Topic Annotations. arXiv. https://doi.org/10.48550/arXiv.2510.01976

Keywords: Values, Value Prediction, Value Classification, LLMs, Subjectivity