Improved Emotional Alignment of AI and Humans: Human Ratings of Emotions Expressed by Stable Diffusion v1, DALL-E 2, and DALL-E 3

Generative AI systems are increasingly capable of expressing emotions via text and imagery. Effective emotional expression will likely play a major role in the efficacy of AI systems -- particularly those designed to support human mental health and wellbeing. This motivates our present research to better understand the alignment of AI expressed emotions with the human perception of emotions. When AI tries to express a particular emotion, how might we assess whether they are successful? To answer this question, we designed a survey to measure the alignment between emotions expressed by generative AI and human perceptions. Three generative image models (DALL-E 2, DALL-E 3 and Stable Diffusion v1) were used to generate 240 examples of images, each of which was based on a prompt designed to express five positive and five negative emotions across both humans and robots. 24 participants recruited from the Prolific website rated the alignment of AI-generated emotional expressions with a text prompt used to generate the emotion (i.e., "A robot expressing the emotion amusement"). The results of our evaluation suggest that generative AI models are indeed capable of producing emotional expressions that are well-aligned with a range of human emotions; however, we show that the alignment significantly depends upon the AI model used and the emotion itself. We analyze variations in the performance of these systems to identify gaps for future improvement. We conclude with a discussion of the implications for future AI systems designed to support mental health and wellbeing.

Developing and Evaluating a Design Method for Positive Artificial Intelligence

As artificial intelligence (AI) continues advancing, ensuring positive societal impacts becomes critical, especially as AI systems become increasingly ubiquitous in various aspects of life. However, developing "AI for good" poses substantial challenges around aligning systems with complex human values. Presently, we lack mature methods for addressing these challenges. This article presents and evaluates the Positive AI design method aimed at addressing this gap. The method provides a human-centered process to translate wellbeing aspirations into concrete practices. First, we explain the method's four key steps: contextualizing, operationalizing, optimizing, and implementing wellbeing supported by continuous measurement for feedback cycles. We then present a multiple case study where novice designers applied the method, revealing strengths and weaknesses related to efficacy and usability. Next, an expert evaluation study assessed the quality of the resulting concepts, rating them moderately high for feasibility, desirability, and plausibility of achieving intended wellbeing benefits. Together, these studies provide preliminary validation of the method's ability to improve AI design, while surfacing areas needing refinement like developing support for complex steps. Proposed adaptations such as examples and evaluation heuristics could address weaknesses. Further research should examine sustained application over multiple projects. This human-centered approach shows promise for realizing the vision of 'AI for Wellbeing' that does not just avoid harm, but actively benefits humanity.

Positive AI: Key Challenges for Designing Wellbeing-aligned Artificial Intelligence

Artificial Intelligence (AI) is transforming the world as we know it, implying that it is up to the current generation to use the technology for ''good.'' We argue that making good use of AI constitutes aligning it with the wellbeing of conscious creatures. However, designing wellbeing-aligned AI systems is difficult. In this article, we investigate a total of twelve challenges that can be categorized as related to a lack of knowledge (how to contextualize, operationalize, optimize, and design AI for wellbeing), and lack of motivation (designing AI for wellbeing is seen as risky and unrewarding). Our discussion can be summarized into three key takeaways: 1) our understanding of the impact of systems on wellbeing should be advanced, 2) systems should be designed to promote and sustain wellbeing intentionally, and 3), above all, Positive AI starts with believing that we can change the world for the better and that it is profitable.