Willem-Paul Brinkman

Reinforcement model that combines worldview of a smoker and health experts

🧪 Preparing to quit, smokers need motivation and build the right competencies. For this, we consider both the worldviews of health experts and smokers. We present a reinforcement learning model that combines these views and can be embedded in a virtual coach.

tinyurl.com/2wta4u83

#AI #ehealth

11.10.2025 15:04 — 👍 2    🔁 1    💬 0    📌 1

“… neutral objective basis” that is just one of the issue, what do we ask the RL model to optimize for? Various optimization goals give different smokers group human attention.

08.06.2025 05:37 — 👍 1    🔁 0    💬 1    📌 0

This is not about ai feedback but who should get feedback from a human coach integrated into ai intervention. Specifically, when the human coach had limited time and can not interact with everyone.

07.06.2025 20:03 — 👍 1    🔁 0    💬 2    📌 0

Psychological, economic, and ethical factors in human feedback for a chatbot-based smoking cessation intervention - npj Digital Medicine npj Digital Medicine - Psychological, economic, and ethical factors in human feedback for a chatbot-based smoking cessation intervention

Who should get human support in AI health apps? 🧪

A new study shows Reinforcement Learning-based human feedback allocation for quitting smoking boosts engagement—but raises ethical questions on fairness and autonomy.
📄 npj Digital Medicine: www.nature.com/articles/s41...

#AI #DigitalHealth

07.06.2025 19:41 — 👍 6    🔁 0    💬 1    📌 0

Being a first generation university graduate, the impact on a career in science Being in the first generation to access Higher Education (First Gen) is a barrier to academic success. First Gens face difficulties transitioning into, completing, and attaining competitive grades in ...

New study from the Women in Supramolecular Chemistry (WISC) revealing the unique challenges resulting from being First Gen (first generation of a family to access Higher Education) in science and showing how these persist at every stage of a career in academia:
pubs.rsc.org/en/content/a...

09.05.2025 14:08 — 👍 76    🔁 41    💬 2    📌 5

Overview of ASAQ constructs

Looking for a validated questionnaire to measure people's experience with a social robot, chatbot, or any artificial social agent? You are in for a treat as the Artificial Social Agent Questionnaire (ASAQ) is out now. 🧪
doi.org/10.1016/j.ij....
asaq.ewi.tudelft.nl

#AI #robots #HCI #HCAI

31.03.2025 19:26 — 👍 4    🔁 0    💬 0    📌 0

Lilobot: A Cognitive Conversational Agent to Train Counsellors at Children’s Helplines - Journal of Medical Systems To equip new counsellors at a Dutch child helpline with the needed counselling skills, the helpline uses role-playing, a form of learning through simulation in which one counsellor-in-training portray...

Counsellors at Children's helplines practice their skills by role-playing with each other, which might not always be easy to organise. We, therefore, proposed a computer agent who acts as a child for role-playing. 🧪

doi.org/10.1007/s109...

#AI #training #helplines #digitalhealth

16.01.2025 21:21 — 👍 10    🔁 1    💬 0    📌 0

Willem-Paul Brinkman

please add me to the science feed

Staff page:
www.tudelft.nl/ewi/over-de-...

Scholar profile
scholar.google.com/citations?us...

ORCID number
orcid.org/0000-0001-84...

ResearchGate profile
www.researchgate.net/profile/Will...

thanks

15.01.2025 19:16 — 👍 1    🔁 0    💬 1    📌 0

📢#PhDPosition Announcement📢
Do you love #Education #Research? Are you looking for an opportunity with a direct impact on student learning? Then come join our IDEE research group about "Progression and Retention of Knowledge and Skills" as #PhD student: www.linkedin.com/jobs/view/40...

05.12.2024 08:11 — 👍 5    🔁 1    💬 0    📌 0