Jesse Hoey

Background: Smart home technologies (SHTs) encompass internet-connected interfaces, sensors, monitors, devices, and appliances, which are networked together to allow for automation. They can facilitate tasks, such as taking medication or issuing fall alerts, and can control the home environment, such as by automating lighting. Their widespread use comes with concerns about power imbalances between users, technology companies, marketers, and state actors regarding data collection, its use and disclosure, and security issues, such as the potential for data breaches. SHT acceptance and adoption are shaped by user attitudes and trust, so understanding these factors is critical. A scoping review conducted by several authors of this paper explored user perceptions of SHTs and identified 4 key themes related to user attitudes: privacy concerns, knowledge of data collection, perceived risks and benefits, and perceived safety. Of the included studies in the review, none explored Canadian SHT users’ attitudes. Thus, little is known about how Canadians perceive and understand the privacy, data collection, and safety elements of their SHTs. Given Canada’s unique demographic diversity and distinct context, examining Canadian perspectives is necessary for advancing this body of research. Objective: This study explored users’ perceptions of SHTs in Canada, with a focus on privacy, the purpose of data collection, risks, and safety. Methods: An online survey was distributed across Canada between March 7 and April 24, 2023, to collect self-reported demographic information and users’ perceptions of SHT privacy, the purpose of data collection, risks and benefits, and safety associated with SHT use. To be eligible for this study, participants had to (1) be adults aged 18 years or older; (2) live in the community; (3) reside in Canada; (4) use at least one SHT; and (5) be comfortable communicating in English. The quantitative data were exported to SPSS (IBM Corp) and the Python programming language for descriptive analysis. Results: Self-reported survey data from a total of 881 SHT users were analyzed. Participants reported user mistrust (294/881, 33.4%), uncertainty (281/881, 31.9%), powerlessness (325/881, 36.9%), and digital resignation (232/881, 26.3%) pertaining to their SHT use. Many users displayed a willingness to trade privacy for perceived benefits, such as convenience, and some highlighted safety as a beneficial feature of SHTs. Contrary to previous internet or smart home research, most participants reported having read their SHT terms of use documents during setup. Conclusions: As the largest national survey of its kind in Canada, this study reveals a complex relationship between Canadians and SHTs, in which privacy concerns coexist with a desire for convenience and safety. These results highlight the need for greater transparency and trust-building measures in SHT design and policy. Understanding users’ perceptions is essential for developing technologies and user-centered frameworks that better align with their values and expectations in Canada’s diverse context.

The affective connotations of words are central to meaning and important predictors of many social processes. As such, understanding the degree to which commercially-available generative language models (LLMs) replicate human judgements of affective connotations may help better understand human-model interactions. LLMs may also serve as useful tools for researchers seeking affective meaning estimates. We test the ability of three LLMs - GPT-4o, Mistral Large, and Llama 3.1 - to estimate human affective connotation ratings of words representing social identities, behaviours, modifiers, and settings in three language cultures: English (US), French (France), and German (Germany). We find that LLM ratings of terms correlate strongly with human ratings. However, their ratings tend to be overly extreme and patterns of correlations between meaning dimensions only loosely approximate those of human ratings. Consistent with previous findings of English-language and American biases in LLMs, we find that LLMs tend to perform better on English terms, though this pattern varies somewhat by meaning dimension and the type of term in question. We explore how LLMs might contribute to scholarship on affective connotations - by acting as tools for measurement - and how scholarship on affective connotations might contribute to generative language models - by guiding exploration of model biases.

Data augmentation is a central component of joint embedding self-supervised learning (SSL). Approaches that work for natural images may not always be effective in medical imaging tasks. This study systematically investigated the impact of data augmentation and preprocessing strategies in SSL for lung ultrasound. Three data augmentation pipelines were assessed: (1) a baseline pipeline commonly used across imaging domains, (2) a novel semantic-preserving pipeline designed for ultrasound, and (3) a distilled set of the most effective transformations from both pipelines. Pretrained models were evaluated on multiple classification tasks: B-line detection, pleural effusion detection, and COVID-19 classification. Experiments revealed that semantics-preserving data augmentation resulted in the greatest performance for COVID-19 classification—a diagnostic task requiring global image context. Cropping-based methods yielded the greatest performance on the B-line and pleural effusion object classification tasks, which require strong local pattern recognition. Lastly, semantics-preserving ultrasound image preprocessing resulted in increased downstream performance for multiple tasks. Guidance regarding data augmentation and preprocessing strategies was synthesized for developers working with SSL in ultrasound.

General Game Playing (GGP) is a field of study in which artificial agents are required to compete in games whose rules are not known until runtime. Monte Carlo Tree Search (MCTS) is popular in this domain for its ability to quickly simulate many instances of a game and run in whatever time it is given. Heuristics may be used to guide these simulations, but since the game is not known in advance, a typical MCTS agent cannot know which heuristics are useful, and must expend precious time to discover them. However, an agent able to take advantage of prior knowledge from other games can do better. This paper extends our publication at the 2024 IEEE Conference on Games [1]. As in that paper, we present a technique for automatically transferring heuristic knowledge between distinct, but similar, games. We show that this leads to better performance in games within the GGP framework, especially when initialization time is short, and we show that negative transfer is possible to detect and avoid. Unique to this paper, we give experimental results for an alternate method of negative transfer protection, and explore the application of our methods to single-player games.

As robots integrate more into daily life, socially aware robots with specific social attributes and behaviors are necessary. This review aims to explore how social norms in Human–Robot Interaction (HRI) impact robot design and human perception. We searched for relevant articles in the following databases: ACM Digital Library, IEEE Digital Library, Scopus, Springer Link, and PsycINFO. After applying inclusion and exclusion criteria, a final set of 69 articles were included in the review. These articles were categorized based on whether they examined norm conformity or norm violations, and were further sorted into 12 categorical norm labels to assist in analysis and comparison. By examining the existing literature, this review uncovers how social norms impact aspects of HRIs like trust, acceptance, and comfort while highlighting the importance of aligning robot design with user expectations. It reveals design challenges such as accounting for cultural variations, context-specific norms, and evolving norms over time. Addressing these challenges has the potential to improve user experiences, promote broader acceptance of robots, and foster successful integration of robots into various domains. The findings contribute to the ongoing discussion on the role of social norms in HRI, offering valuable insights and a foundation for future research.

As robots increasingly permeate diverse domains like healthcare, education, service industries and homes, accurately understanding humans’ responses to and behaviour towards robots is crucial. While many human-robot interaction (HRI) studies focus on either quantitative or qualitative approaches, we advocate a mixed-method approach. This study investigated robot norm violations by implementing a scenario where a mobile manipulator robot and a human, in-person, carry out a physical, competitive task. Sixty-two participants were recruited and randomly assigned to either an experimental or a control condition (balanced for age/gender). The scenario was a competitive scavenger hunt game where participants took turns with a robot. We investigated the robot behaviours’ effects on trust, discomfort, competence, enjoyment, participant behaviour and physiological changes. The mixed-method approach integrated physiological measurements, behavioural observations and qualitative responses, thus offering a comprehensive account of HRI dynamics in the context of norm violations. Questionnaire results reveal significant shifts in human perceptions and attitudes when social norms are violated by robots, compared to a norm-compliant control condition. Specifically, trust and enjoyment decrease, discomfort increases and the robot’s perceived competence is compromised. These findings are extended through additional analyses of participants’ physiological changes, behaviours and responses to open-ended questions. Behavioural observations indicated increased verbal engagement and emotional responses, while physiological data showed elevated stress levels in the experimental group. Our study highlights the advantage of a mixed-methods approach combining different qualitative and quantitative data, providing a more comprehensive picture of participants’ perceptions of a robot, and how they react and respond to robot norm violations.

This paper explores the notion of complementarity in the modeling of social systems. Complementary variables in physics exhibit a duality , and similar dualities are found in the analysis of social, political, cultural, and neurophysiological structures. In this paper, I show that the management of uncertainty in a hierarchical model exhibits certain dualities that closely parallel those observed in social systems. I argue that, due to the necessity of coordination within collectives, agents will mirror each other to a large extent, and will develop heuristics and tactics that are aligned with how each agent is managing uncertainty dualities. I connect sociological literature on social structures with neuroscientific, economic, and psychological developments, and show a simplified derivation of these connections from free energy principles. I then explore how these connections can be used to gain insights into observable socio-cultural processes.

BACKGROUND Smart Home Technology (SHT) encompasses Internet-connected interfaces, sensors, monitors, devices, and appliances, which are networked together to allow for automation as well as control of the home environment. They can facilitate tasks such as taking medication or send emergency fall alerts. However, their widespread use comes with concerns of power imbalances between users, technology companies, marketers, state actors, and others regarding data collection, its use and disclosure, as well as security issues such as the potential for data breaches. Despite this, little is known about how Canadians perceive and understand their SHTs. Given Canada’s unique demographic diversity and distinct context, examining Canadian perspectives is necessary to advancing this body of research. OBJECTIVE This paper explores user perceptions of SHTs in Canada with a focus on four themes: privacy, purpose of data collection, risks and benefits, and safety. METHODS An online cross-sectional survey was conducted between March 7 – April 24, 2023 across Canada to collect self-reported demographic information and perceptions around the four aforementioned themes through multiple-choice and optional short response questions. The quantitative data was exported into SPSS and Python programming language for further analysis. RESULTS Survey data from a total of 881 SHT users was analysed. The presence of privacy cynicism was displayed via user mistrust (294/881, 33%), uncertainty (281/881, 32%), powerlessness (325/881, 37%), and digital resignation (232/881, 26%) as self-reported by users. Many users displayed a willingness to trade privacy for perceived benefits, such as convenience (503/881, 57%). Users also flagged enhanced safety and daily convenience as a beneficial feature of SHTs (492/881, 56%). Contrary to previous Internet or smart home research, most (801/881, 91%) participants reported having read their SHT Terms of Use documents upon setup. CONCLUSIONS This study illustrates themes of privacy cynicism and digital resignation within Canadian users, which are prevalent within an emerging body of related literature on Internet platforms more generally, and highlights ways in which to mitigate these patterns. The gap between user privacy preferences and options underscores the need for stronger user-centric design and data protection regulation. These insights and suggestions provide valuable guidance for policymakers and industry stakeholders navigating the complex landscape of SHT adoption.

Smart Home Technologies (SHTs) have recently become popular for a variety of purposes, including healthcare, entertainment, and convenience, among others. While SHT manufacturers promise to provide a range of services relating to home security, health and wellness, automated domestic tasks, entertainment, and beyond, user perceptions vary widely in terms of benefits and drawbacks. Moreover, surveillance studies researchers have warned against normalizing technologies that may exacerbate uneven power dynamics between users and household members, marketing companies, insurance brokers, law enforcement, and others. Through an analysis of the interdisciplinary literature stemming from computer science and engineering, gerontology, the social sciences, and related fields, we explore the extent to which these potential risks and related concerns are reflected upon by smart home users. This scoping review aims to explore SHT user perceptions of privacy attitudes, the purposes of smart home surveillance, risks and benefits, and impacts on home safety. Through our review of sixty-eight relevant studies, we found that many smart home users reported satisfaction over perceived benefits such as an increased sense of safety and home security. Many others displayed limited understandings of data collection practices or expressed privacy concerns. Nonetheless, SHT usage prevailed among these users. Others report a perceived trade-off between privacy and other factors, such as convenience, and some may have resorted to privacy cynicism, a coping mechanism for dealing with ubiquitous surveillance. In order to better understand SHT adoption trends despite concerns, exploring the conflict between user perceptions of privacy, understanding of SHT data collection purposes, risks and benefits, and home safety, is essential.