A5053022533- Speech and dialogue systems
- AI in Service Interactions
- Language, Metaphor, and Cognition
- Social Robot Interaction and HRI
- Language, Discourse, Communication Strategies
- Behavioral Health and Interventions
- Technology Adoption and User Behaviour
- Digital Marketing and Social Media
- Topic Modeling
- Interactive and Immersive Displays
- Impact of Technology on Adolescents
- ICT in Developing Communities
- Gambling Behavior and Treatments
- Action Observation and Synchronization
- Educational Games and Gamification
- Usability and User Interface Design
- Innovative Human-Technology Interaction
- Ethics and Social Impacts of AI
University College Dublin
2019-2025
Conversational agents promise conversational interaction but fail to deliver. Efforts often emulate functional rules from human speech, without considering key characteristics that conversation must encapsulate. Given its potential in supporting long-term human-agent relationships, it is paramount HCI focuses efforts on delivering this promise. We aim understand what people value and how should manifest agents. Findings a series of semi-structured interviews show make clear dichotomy between...
Speech interfaces are growing in popularity. Through a review of 68 research papers this work maps the trends, themes, findings and methods empirical on speech HCI. We find that most studies usability/theory-focused or explore wider system experiences, evaluating Wizard Oz, prototypes, developed systems by using self-report questionnaires to measure concepts like usability user attitudes. A thematic analysis found HCI focuses nine key topics: production, modality comparison, assistive...
Advances in natural language processing and understanding have led to a rapid growth the popularity of conversational user interfaces (CUIs). While CUIs introduce novel benefits, they also yield risks that may exploit people's trust. Although research looking at unethical design deployed through graphical (GUIs) established thorough so-called dark patterns, there is need continue this discourse within CUI community understand potentially problematic interactions. Addressing gap, we...
Recent work has looked to understand user perceptions of speech agent capabilities as dialogue partners (termed partner models), and how this affects interaction. Yet, model effects are currently inferred from language production no metrics available quantify these subjective more directly. Through three phases work, we develop validate the Partner Modelling Questionnaire (PMQ): an 18-item self-report semantic differential scale designed reliably measure people’s models non-embodied...
The assumptions we make about a dialogue partner's knowledge and communicative ability (i.e. our partner models) can influence language choices. Although similar processes may operate in human-machine dialogue, the role of design shaping these models, their subsequent effects on interaction are not clearly understood. Focusing synthesis design, conduct referential communication experiment to identify impact accented speech lexical choice. In particular, focus whether encourage use...
Designers commonly use gamification to improve the frequency of engagement with apps, but often fail consider impact placement on reward value. As rewards tend depreciate if delayed (termed temporal discounting), placing a further into future can significantly affect its ability motivate behaviour. We examine most effective gamified so as reduce discounting and increase an application is used. In two online studies, users were asked choose between fictional budget tracking applications that...
Recent work has looked to understand user perceptions of speech agent capabilities as dialogue partners (termed partner models), and how this affects interaction. Yet, currently model effects are inferred from language production no metrics available quantify these subjective more directly. Through three studies, we develop validate the Partner Modelling Questionnaire (PMQ): an 18-item self-report semantic differential scale designed reliably measure people's models non-embodied interfaces....
A lot of academic and industrial HCI work has focused on making interactions easier less effortful. As the potential risks optimising for effortlessness have crystallised in systems designed to take advantage way human attention cognition works, researchers practitioners wondered whether increasing 'friction' interactions, them more effortful might make sense some contexts. The goal this special interest group is provide a forum discuss advance theoretical underpinnings friction, relation...
Human-machine dialogue (HMD) research debates the degree to which language production in this context is egocentric or allocentric. That is, a person might take machine's perspective into account. Our study aims identify whether users produce allocentric within speech-based HMD when there asymmetry information available both partners. Through an adapted referential communication task, we manipulated presence absence of visual distractors and occlusions, similarly previous tasks used...
Current work supposes that people tend to adapt their language allocentrically, taking into account the perceived limitations of partners, when talking computers. Yet, debates in human-human dialogue (HHD) research suggest may also act egocentrically producing dialogue. Our aims identify whether, similar HHD, users produce egocentric within speech-based human-computer (HCD) interactions and how this behaviour compares interaction with human partners. Through two controlled experiments using...
The frequency with which people interact technology means that users may develop interface habits, i.e. fast, automatic responses to stable cues. Design guidelines often assume habits are beneficial. However, we lack quantitative evidence of how the development actually affect user performance and an understanding changes in design habit development. Our work quantifies effect formation disruption on interaction. Through a forced choice lab study task (n=19) wild deployment (n=18)...