Circular Image

H. Gu

info

Please Note

6 records found

Analysing Language Use in Designing: Practices and Performance

Journal article (2026) - Senthil Chandrasegaran, Lisa Perez Elzey, Heng Gu, Nathan Crilly, Terresa Hardaway, Vivek Rao, Peter Lloyd
The role of language in designing is manifold, including but not limited to representing all aspects of design, enacting roles in design processes, and establishing shared meaning. With the advent of large language models (LLMs), the role of language has further expanded, affording new ways to perform and represent design. This theme track presents five papers that explore how designers use language and language models. We identify themes that cut across these papers to show how language can be used, constrained, adapted, and supplemented in different stages, processes, and domains of designing. ...

Examining How Conversational Agents' Linguistic Expressions of Personality Affect User Perceptions and Decisions

Large Language Model-powered conversational agents (CAs) are increasingly capable of projecting sophisticated personalities through language, but how these projections affect users is unclear. We thus examine how CA personalities expressed linguistically affect user decisions and perceptions in the context of charitable giving. In a crowdsourced study, 360 participants interacted with one of eight CAs, each projecting a personality composed of three linguistic aspects: attitude (optimistic/pessimistic), authority (authoritative/submissive), and reasoning (emotional/rational). While the CA's composite personality did not affect participants' decisions, it did affect their perceptions and emotional responses. Particularly, participants interacting with pessimistic CAs felt lower emotional state and lower affinity towards the cause, perceived the CA as less trustworthy and less competent, and yet tended to donate more toward the charity. Perceptions of trust, competence, and situational empathy significantly predicted donation decisions. Our findings emphasize the risks CAs pose as instruments of manipulation, subtly influencing user perceptions and decisions. ...
Journal article (2026) - J.S. Love, Eric Heng Gu, Jeroen Vandommele
This paper explores the design and implementation of CuratorBot, an interactive chatbot developed to enhance visitor engagement in cultural heritage institutions using generative large language models. Positioned as a conversational guide, CuratorBot simulates a docent's role of enabling personalised, dynamic dialogues about historical artefacts, specifically focusing on the Dutch National Library's Visboeck manuscript. CuratorBot offers visitors the opportunity to actively interact with cultural heritage by having a conversation with a computer partner.
Through iterative design experiments, user interaction observations and surveys, we assess the chatbot's capacity to foster curiosity, support free-choice learning and facilitate human-like conversations, thereby making cultural experiences more accessible and engaging for a broader audience. The development process involved continuous user feedback which highlighted key areas of improvement and adaptation to better serve visitor needs. The paper addresses opportunities and challenges of using LLM-based conversational agents in heritage settings and offers insights for future development of visitor engagement tools with embedded machine learning. We also discuss broader implications of incorporating generative conversational interfaces in GLAMs by examining how such tools can contribute to the
evolving landscape of digital cultural heritage. ...

A Longitudinal Study of Design Trajectories in Future Mobility Project Briefs

Conference paper (2026) - E.Y. Kim, Eric Heng Gu
The mobility sector increasingly operates under conditions characterized by persistent uncertainty, rapid technological change, and complex stakeholder dynamics, often described as volatile, uncertain, complex, and ambiguous (VUCA) contexts. Building on prior work that examined design process trajectories in airport ecosystem cases, we introduce Dynamic Stability framework as a theoretical lens to interpret how design teams balance exploration and coherence in open-ended future mobility design project contexts. This paper examines how novice design teams navigate these complex challenges through a longitudinal analysis of 80 student projects (61 coded) from four annual offerings (2021–2025) of a project-based future mobility design course at a major research university in the Netherlands. Our longitudinal analysis reveals recurring design intervention patterns of reframing, integration of multi stakeholder views, and situational adoption of transition heuristics, and the cross-tabulation of innovation level (project; service; and system) and intervention type (Redesign; Reframe; Repurpose; and Reimagine). System-level outcomes appear exclusively in multimodal and emerging domains. Also, our research reveals that product outcomes are predominantly reached via Redesign, Service outcomes via Reframe, and System outcomes exclusively via Reframe or Reimagine. Our findings offer implications for design pedagogy, curriculum innovation, and dynamic stability theory and framework building in complex and extreme system designs. ...

Insights from designers’ interactions with persona-based chatbots

Journal article (2025) - Eric Heng Gu, Senthil Chandrasegaran, Peter Lloyd
Personas are hypothetical representations of real-world people used as storytelling tools to help designers identify the goals, constraints, and scenarios of particular user groups. A well-constructed persona can provide enough detail to trigger recognition and empathy while leaving room for varying interpretations of users. While a traditional persona is a static representation of a potential user group, a chatbot representation of a persona is dynamic, in that it allows designers to “converse with” the representation. Such representations are further augmented by the use of large language models (LLMs), displaying more human-like characteristics such as emotions, priorities, and values. In this paper, we introduce the term “Synthetic User” to describe such representations of personas that are informed by traditional data and augmented by synthetic data. We study the effect of one example of such a Synthetic User – embodied as a chatbot – on the designers’ process, outcome, and their perception of the persona using a between-subjects study comparing it to a traditional persona summary. While designers showed comparable diversity in the ideas that emerged from both conditions, we find in the Synthetic User condition a greater variation in how designers perceive the persona’s attributes. We also find that the Synthetic User allows novel interactions such as seeking feedback and testing assumptions. We make suggestions for balancing consistency and variation in Synthetic User performance and propose guidelines for future development. ...

Soundscapes for visually impaired visitors

Conference paper (2024) - Angeliki Antoniou, J.S. Love, Ioanna Lykourentzou, Heng Gu, Maria Stathi
The paper presents the initial stages of a project that wishes to create soundscapes for people with visual impairments at the archaeological site of Souriza-Agrileza (Greece). The students of a music school collaborated with the archaeologists from the local ephorate of antiquities in order to provide appropriate sound clips that would be incorporated in the site, thus “translating” what students see to sounds and music for visitors with disabilities. In addition, the paper includes a relevant literature review that guided the design of the project. ...