Filtered by themeControlled experiment7 papersclear ✕

Shaping Human-AI Collaboration: Varied Scafolding Levels in Co-writing with Language ModelsSomayeh Molaei · 2024Advances in language modeling have paved the way for novel human-AI co-writing experiences. This paper explores how vary­ ing levels of scafolding from large language models (LLMs) shape the co-writing process. Employing a within-subjects feld experi­ ment with a Latin square design, we asked participants (N=131) to respond to argumentative writing prompts under three randomly sequenced conditions: no AI assistance (control), next-sentence sug­ gestions (low scafolding), and next-paragraph suggestions (high scafolding). Our fndings reveal a U-shaped impact of scafold­ ing on writing quality and productivity (words/time). While low scafolding did not signifcantly improve writing quality or productivity, high scafolding led to signifcant improvements, es­ pecially benefting non-regular writers and less tech-savvy users. No signifcant cognitive burden was observed while using the scaf­ folded writing tools, but a moderate decrease in text ownership and satisfaction was noted. Our results have broad implications for the design of AI-powered writing tools, including the need for personalized scafolding mechanisms. CCS CONCEPTS • Human-centered computing → Collaborative and social computing design and evaluation methods; Empirical studies in collaborative and social computing.

UX of AI & PersonalizationResearch Papers

Application of Artificial Intelligence in Interactive UI DesignSha Liang · 2024The purpose of this study is to deeply explore the influence of artificial intelligence (AI) application in interactive User Interface (UI) design, and evaluate its effect in conceptual design, prototype design and final design through experiments and analysis. By introducing generative design tools, machine learning algorithms and sentiment analysis technology, this study evaluates the role of AI in improving design efficiency, personalizing user experience, increasing creativity and enhancing emotional resonance of users. In the evaluation of design effect, it is found that the effect score is significantly improved after the introduction of AI in each design stage. The design scheme generated by the designer through AI is more in line with the needs of users, the design accuracy is improved, and the creativity is also increased compared with the traditional design. In terms of personalized user experience, we use machine learning algorithm to adjust interface elements according to user behavior to provide a more personalized user experience. The experimental results show that personalized design can significantly improve user satisfaction and interaction efficiency. Through the emotional analysis technology, the language and emotional tone of the design are adjusted, and the emotional resonance of users is improved. Designers can better express their emotions and make the design more in line with the emotional needs of users. On the whole, this study provides an in-depth empirical study on the application of AI in UI design, and provides beneficial enlightenment for future intelligent design and user experience research.

UX of AI & PersonalizationResearch Papers

Assessing Human-AI Interaction Early through FactorialMIHAELA VORVOREANU, DEREK DEBELLIS et al. · 2023This work contributes a research protocol for evaluating human-AI interaction in the context of specific AI products. The research protocol enables UX and HCI researchers to assess different human-AI interaction solutions and validate design decisions before investing in engineering. We present a detailed account of the research protocol and demonstrate its use by employing it to study an existing set of human-AI interaction guidelines. We used factorial surveys with a 2 × 2 mixed design to compare user perceptions when a guideline is applied versus violated, under conditions of optimal versus sub-optimal AI performance. The results provided both qualitative and quantitative insights into the UX impact of each guideline. These insights can support creators of user-facing AI systems in their nuanced prioritization and application of the guidelines.

UX of AI & PersonalizationResearch Papers

How Do Visual Explanations Foster End Users' Appropriate Trust in Machine Learning?Fumeng Yang · 2020We investigated the effects of example-based explanations for a machine learning classifier on end users’ appropriate trust. We explored the effects of spatial layout and visual representation in an in-person user study with 33 participants. We measured partici- pants’ appropriate trust in the classifier, quantified the effects of different spatial layouts and visual representations, and observed changes in users’ trust over time. The results show that each expla- nation improved users’ trust in the classifier, and the combination of explanation, human, and classification algorithm yielded much better decisions than the human and classification algorithm sepa- rately. Yet these visual explanations lead to different levels of trust and may cause inappropriate trust if an explanation is difficult to un- ∗Fumeng Yang was a PhD intern at Pacific Northwest National Laboratory when conducting this research. †Jean Scholtz retired from Pacific Northwest National Laboratory September 2018. Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the owner/author(s). IUI ’20, March 17–20, 2020, Cagliari, Italy © 2020 Copyright held by the owner/author(s). ACM ISBN 978-1-4503-7118-6/20/03. [https://doi.org/10.1145/3377325.3377480](https://doi.org/10.1145/3377325.3377480) derstand. Visual representation and performance feedback strongly affect users’ trust, and spatial layout shows a moderate effect. Our results do not support that individual differences (e.g., propensity to trust) affect users’ trust in the classifier. This work advances the state-of-the-art in trust-able machine learning and informs the design and appropriate use of automated systems. CCS CONCEPTS • Human-centered computing →Empirical studies in HCI; Information visualization; Empirical studies in visualization; Visualization design and evaluation methods; • Computing method- ologies →Supervised learning by classification.

UX of AI & PersonalizationResearch Papers

Can emotional design really evoke emotion in multimedia learning?2020The aim of this study was to investigate the effects of emotional design on learners’ performance and emotions. If emotional design has any effects on learners’ performance and emotions, then we attempted to explore dimensions that are accounted for such effects. 316 Chinese university students participated in this study. The students were divided into two groups: NED group - students in this group learned material based on neutral design, and PED group - students in this group learned material based on positive design. We explored the differences between two groups in student learning performance as well as emotion. Prior knowledge, retention, and transfer tests were also carried out and outcomes were compared across two groups. In addition, student emotion was measured using a positive affect scale and biofeedback instruments. The results showed that PED group outperformed NED group on retention and transfer tests. However, insignificant difference was found between two groups on student emotion. Our results suggest that, although the effect of emotional design was insignificant on student emotion, it was significant on student learning performance (i.e. on retention and transfer tests). Based on our results, several implications were drawn and suggestions were made for educators and researchers.

Emotional DesignResearch Papers

Emotional Design in Multimedia Learning: How Emotional Intelligence Moderates Learning OutcomesJeya Amanth · 2016This study is designed as a preliminary study to explore the effects of emotional intelligence (EI) on achievement, perceived intrinsic motivation and perceived satisfaction when expose to an emotional designed Multimedia Learning Environment (MLE) that was designed to induce either positive, neutral or negative emotions. All three designs had similar content and narration but differed in visual element such as colour, font size, font style and images. Based on the findings, it was reported that students performed better in the design used to induce negative emotion (NegD design) followed by the positive (PosD) and Neutral (NeuD). There is no significant difference in levels of emotional intelligence towards these learning outcomes; however, students with Low EI performed better overall. EI only qualified perceived satisfaction when using a MLE designed to induce emotions and it was found that students with Low EI preferred the design that induces positive emotions. In addition, High EI students favored designs with emotionality (positive or negative) compared to neutral design. Index Terms—Emotional Design, Engineering Education, Emotional Intelligence, Multimedia- Based Learning, Aesthetics.

Emotional DesignResearch Papers

Towards customized emotional design: An explorative study of user personality and user interface skin preferences2005Two key elements in the area of cognitive ergonomics are user-system performance and the user similarity. However, with the introduction of skinnable user interfaces, a technology that gives the user interface a chameleon-like ability, elements such as aesthetic, fun, and especially user individuality and identity become more important. This paper presents two explorative studies on user personality in relation to skin preferences. In the studies participants were asked to rate their preference of a set of Windows Media Player skins and to complete the BIS/BAS and the IPIP-NEO personality inventories. The results of the first study suggest colour and similarity-attraction as two possible underlying factors for the correlations found between personality traits and skin preferences. The results of the second study partly confirm these findings, however not for similar personality traits and skin types correlations.

Emotional DesignResearch Papers