Collecting data is one of the bottlenecks of Human-Computer Interaction (HCI) and user experience (UX) research. In this poster paper, we explore and critically evaluate the potential of large-scale neural language models like GPT-3 in generating synthetic research data such as participant responses to interview questions. We observe that in the best case, GPT-3 can create plausible reflections of video game experiences and emotions, and adapt its responses to given demographic information. Compared to real participants, such synthetic data can be obtained faster and at a lower cost. On the other hand, the quality of generated data has high variance, and future work is needed to rigorously quantify the human-likeness, limitations, and biases of the models in the HCI domain. CCS CONCEPTS• Human-centered computing → Empirical studies in HCI.
Computational interaction and user modeling is presently limited in the domain of emotions. We investigate a potential new approach to computational modeling of emotional response behavior, by using modern neural language models to generate synthetic self-report data, and evaluating the human-likeness of the results. More specifically, we generate responses to the PANAS questionnaire with four different variants of the recent GPT-3 model. Based on both data visualizations and multiple quantitative metrics, the human-likeness of the responses increases with model size, with the largest Davinci model variant generating the most human-like data. CCS CONCEPTS• Human-centered computing → Empirical studies in HCI.
Love is an essential biological, psychological, sociological, and religious phenomenon. Using various conceptual models, philosophers have often distinguished between different types of love, such as self-love, romantic love, friendship love, love of God, and neighborly love. Psychologists and neuroscientists on the other hand have thus far focused predominantly on understanding the emotions and behavioural and neural mechanisms associated with romantic love and parental love. We do not yet know how the models construed by philosophers are related to actual experiences of love, and to which extent they are merely nominal creations connecting phenomena that in fact have little to do with each other. We lack empirical knowledge of how different types of love are experienced as embodied feelings, and how these experiences are related to one another. Here we distinguished between 27 different types of love. Using self-report methods, we measured 1) how subjective feelings of different types of love are topographically embodied; 2) how different types of love are associated with self-reported emotional valence, strength of the bodily and mental experience, association with touch time elapsed since last experienced, and controllability; and 3) how similar different types of love feel. Our similarity results suggest that the 27 types of love cluster into a) interpersonal love and b) love for ideas and non-human animals. The topographical bodily sensations associated with the love types form a continuum from strongly to weakly felt loves.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.