Simon D'Alfonso

NarrativeSense: Predicting Affective States in University Students through Smartphone Sensing and Contextual Narratives | ACM Transactions on Computing for Healthcare Mental health challenges are increasingly prevalent among university students, yet often go undetected due to reliance on traditional assessments that are subjective, infrequent, and lack behavioral context. Digital phenotyping through passively collected ...

New paper involving AWARE - NarrativeSense: Predicting Affective States in University Students through Smartphone Sensing and Contextual Narratives dl.acm.org/doi/10.1145/...

Part 1: How do LLMs work? YouTube video by Andrew Perfors

I just created a series of seven deep-dive videos about AI, which I've posted to youtube and now here. 😊

Targeted to laypeople, they explore how LLMs work, what they can do, and what impacts they have on learning, well-being, disinformation, the workplace, the economy, and the environment.

World Logic Day 14 January

Happy World Logic Day: www.unesco.org/en/days/worl...

After "AI": Anticipating a post-LLM science & technology revolution I, for one, welcome the coming age of the post-LLM-datacenter-overinvestment-bust-fueled backyard GPU supercomputer revolution.

I’m cautiously optimistic about what comes after the current AI frenzy - despite what’s going on. With proper guardrails, it could still fuel real science and meaningful innovation.
#AI #AIFuture #Innovation

Who would be the right people to ask?

'Claude never sleeps': The new AI therapists that don't judge, get tired or need an appointment Artificial intelligence chatbots like ChatGPT are embedded in modern life, with some Australians using them to help work through PTSD and toxic work environments.

www.abc.net.au/news/2025-11...

Client101 — Simulation Platform for Psychotherapy Training Client101 is an edtech platform of simulated mental‑health clients that helps psychotherapy and online counselling students practice safely and receive objective feedback.

client101.net/home

While Silicon Valley is investing tens of billions of dollars chasing the artificial general intelligence dream, academic computing research in the U.S. is facing a severe drought. . cacm.acm.org/opinion/comp...

Nobel Prize-Winning Philosopher Bertrand Russell Biopic in Development, Amanda Curdt-Christiansen to Pen Script (EXCLUSIVE) Nobel Prize winner Bertrand Russell gets first feature biopic.

variety.com/2025/film/ne...

Leveraging Large Language Models for Simulated Psychotherapy Client Interactions: Development and Usability Study of Client101 Background: In recent years large language models (LLMs) have shown remarkable ability to generate human-like text. One potential application of this capability is using LLMs to simulate clients in a mental health context. This research presents the development and evaluation of Client101, a web conversational. platform featuring LLM-driven chatbots designed to simulate mental health clients. Objective: Develop and test a web-based conversational psychotherapy training tool designed to closely resemble clients with mental health issues. Methods: We used GPT-4 and prompt engineering techniques to develop chatbots that simulate realistic client conversations. Two chatbots were created based on clinical vignette cases: one representing a person with depression and the other, a person with generalized anxiety disorder. 16 mental health professionals were instructed to conduct single sessions with the chatbots using a cognitive behavioral therapy framework; a total of 15 sessions with the anxiety chatbot and 14 with the depression chatbot were completed. After each session, participants completed an 18-question survey assessing the chatbot’s ability to simulate the mental health condition and its potential as a training tool. Additionally, we used the Linguistic Inquiry and Word Count (LIWC) tool to analyze the psycholinguistic features of the chatbot conversations related to anxiety and depression. These features were compared to those in a set of webchat psychotherapy sessions with human clients —42 sessions related to anxiety and 47 related to depression—using an independent samples t-test. Results: Participants' survey responses were predominantly positive regarding the chatbots' realism and portrayal of mental health conditions, with over 80% selecting either "strongly agree" or "agree" that the chatbots provided a realistic, engaging, coherent, and convincing narrative typical of clients with anxiety or depression. The statistical analysis of LIWC psycholinguistic features revealed significant differences between chatbot and human therapy transcripts for 3 of 8 anxiety-related features: Negations (t(56)=4.03, P=.001), Family (t(56)=-8.62, P=.001), and Negative Emotions (t(56)=-3.91, P=.002). The remaining 5 features—Sadness, Personal Pronouns, Present Focus, Social, and Anger—did not show significant differences. For depression-related features, 4 out of 9 showed significant differences: Negative Emotions (t(60)=-3.84, P=.003), Feeling (t(60)=-6.40, P< .001), Health (t(60)=-4.13, P=.001), and Illness (t(60)=-5.52, P

New in JMIR MedEdu: Leveraging Large Language Models for Simulated Psychotherapy Client Interactions: Development and Usability Study of Client101

StudentSense: Primary outcomes of a smartphone digital phenotyping study of university students in Australia University students face increasing mental health challenges, yet traditional assessment methods often lack timeliness and contextual relevance. This …

www.sciencedirect.com/science/arti... StudentSense: Primary outcomes of a smartphone digital phenotyping study of university students in Australia

Leveraging Large Language Models for Simulated Psychotherapy Client Interactions: Development and Usability Study of Client101 Background: In recent years large language models (LLMs) have shown remarkable ability to generate human-like text. One potential application of this capability is using LLMs to simulate clients in a ...

mededu.jmir.org/2025/1/e68056

How do users of a mental health app conceptualise digital therapeutic alliance? A qualitative study using the framework approach - BMC Public Health Background Self-guided mental health smartphone applications (apps) have the potential to increase access to evidence-based psychological interventions and reduce the burden on staff resources in stra...

link.springer.com/article/10.1... How do users of a mental health app conceptualise digital therapeutic alliance? A qualitative study using the framework approach

OpenAI Says It's Hired a Forensic Psychiatrist as Its Users Keep Sliding Into Mental Health Crises OpenAI said it's hiring a forensic psychiatrist to help research the effects of its AI products on users' mental health.

futurism.com/openai-foren...

Therapy shock: Pioneering mental health chatbot is shutting down A landmark AI therapy chatbot is closing down on June 30, and industry experts believe that its demise is most likely in response to the challenges of delivering impactful mental health services and n...

newatlas.com/mental-healt...

📢 Announcing the 10th Mental Health Workshop at Ubicomp/ISWC 2025 in Espoo, Finland, October 12th or 13th (TBD).

📝 We invite papers exploring the role of ubiquitous computing + mental health in clinical and/or general populations.

📅 Submission deadline June 13. More ubicomp-mental-health.github.io

Synthetic Empathy: Generating and Evaluating Artificial Psychotherapy Dialogues to Detect Empathy in Counseling Sessions Daniel Cabrera Lozoya, Eloy Hernandez Lua, Juan Alberto Barajas Perches, Mike Conway, Simon D’Alfonso. Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 20...

Synthetic Empathy: Generating and Evaluating Artificial Psychotherapy Dialogues to Detect Empathy in Counseling Sessions aclanthology.org/2025.clpsych...

Sage Journals: Discover world-class research Subscription and open access journals from Sage, the world's leading independent academic publisher.

New publication from a study that used AWARE - "SmartSense-D: A safety, feasibility, and acceptability pilot study of digital phenotyping in young people with major depressive disorder" (journals.sagepub.com/doi/10.1177/...)

We need to stop pretending AI is intelligent – here’s how AI may appear human, but it is an illusion we must tackle.

#AI isn’t human, no matter how advanced it appears. It processes patterns rather than thinking. Let's move away from the saviour narrative and recognise AI for the powerful tool it is. With human oversight, clear guidelines, and solid ethics, that's where real value emerges. #AIEthics #ResearchSky

‘She helps cheer me up’: the people forming relationships with AI chatbots From virtual ‘wives’ to mental health support, more than 100m people are using personified chatbots

While research found most interviewees gained validation from close relationships with chatbots... these were hollowed out versions of friendship: providing entertainment when bored..."There’s was no sense of growth or development or challenging yourself.”
www.theguardian.com/technology/2...

Could your next therapist be a robot? | Particle The use of artificial intelligence in psychotherapy is on the rise – but it comes with a warning.

Could your next therapist be a robot? particle.scitech.org.au/health/could...

Clinical decision support systems in mental health: A scoping review of health professionals’ experiences Clinical decision support systems (CDSSs) have the potential to assist health professionals in making informed and cost-effective clinical decisions w…

www.sciencedirect.com/science/arti...

pacja.org.au/article/1298... Balancing Ethics and Opportunities: The Role of AI in Psychotherapy and Counselling

We’re hiring! The UQ School of EECS is recruiting a Lecturer/Senior Lecturer (Asst. Prof.) in Applied AI for a continuing teaching & research role. Join us to help build a new Centre of Excellence in AI & Data Science between UQ (Brisbane, Australia) & Thapar Institute (India).

Development of a digital therapeutic alliance scale (MM-DTA) in the context of fully automated mental health apps Therapeutic alliance (TA) refers to the relationship between a therapist and a client in face-to-face therapy and is an essential ingredient in successful psychological therapy outcomes. With the a...

www.tandfonline.com/doi/full/10.... Development of a digital therapeutic alliance scale (MM-DTA) in the context of fully automated mental health apps

Workshop A: FROM PIXELS TO PSYCHOLOGY: DECODING BEHAVIOUR THROUGH SMARTPHONE SENSING ubicomp.oulu.fi/ubiss2025/wo...

Nomophobia, Psychopathology, and Smartphone-Inferred Behaviors in Youth With Depression: Longitudinal Study Background: Smartphones have become an indispensable part of people’s lives, and the fear of being without them, what has been termed “no mobile phone phobia” (nomophobia), is a growing phenomenon. Th...

Nomophobia, Psychopathology, and Smartphone-Inferred Behaviors in Youth With Depression: Longitudinal Study formative.jmir.org/2025/1/e57512

Home WELCOME TO UbiComp / ISWC 2025

www.ubicomp.org/ubicomp-iswc...

If you know your Plato (and I hope you do), "efficiency" has been cover for authoritarianism since ancient times. It's all there in the "Republic."

Designing Technologies for Value-based Mental Healthcare: Centering Clinicians' Perspectives on Outcomes Data Specification, Collection, and Use Health information technologies are transforming how mental healthcare is paid for through value-based care programs, which tie payment to data quantifying care outcomes. But, it is unclear what outco...

Really excited to share a preprint of our upcoming CHI 2025 paper on designing technologies for value-based mental healthcare. I've been interested in how HCI can improve health services more broadly, and this paper takes a first step towards that.

www.arxiv.org/abs/2502.01829