From April 26 to May 1, 2025, the e-Lite group will attend the ACM CHI conference on Human Factors in Computing Systems in Yokohama, Japan.
Luigi, Alberto, Tommaso, Luca, and Rob will be there in person. If you see any of us, feel free to say hello: we're always happy to chat! 😊
The team will present a full paper on scientific writing with AI, along with two Late-Breaking Works (LBWs) on digital wellbeing.
We are excited to announce that our latest research, The Digital Attention Heuristics: Supporting the User's Attention by Design, has been published in the prestigious ACM Transactions on Computer-Human Interaction (TOCHI). The research, led by Alberto Monge Roffarello and Luigi De Russis from Politecnico di Torino, in collaboration with Kai Lukoff from Santa Clara University, introduces a set of eight design heuristics aimed at preserving user attention and fostering digital wellbeing.
The paper addresses the growing concern around "attention-capture" designs employed by tech companies, which often exploit users' psychological vulnerabilities to maximize engagement. Examples of these attention-capture designs include the infinitely scrollable newsfeed of Instagram or the autoplay of the next video on YouTube. Unlike traditional digital wellbeing interventions that place the burden of digital self-control on users, this research shifts the focus to designers, offering actionable heuristics to create interfaces that respect users' attention and time by default.
We are thrilled to announce the publication of our latest research, "Supporting Teachers, Engaging Students: A Collaborative Model for K-12 Computing Education," in the Entertainment Computing journal.
The work shares our experience with the Batti il 5! national project, which aimed to strengthen computing skills in primary schools in the Mirafiori Sud district of Turin. In the paper, in particular, we address key challenges in integrating Computational Thinking (CT) into primary school curricula, such as teacher training and curriculum development. Through the design and evaluation of an introductory coding course for 4th-grade students—where children were guided to create a simple Scratch video game like the one shown in the figure—we explored how project-based learning and a collaborative approach involving experts, teachers, and high-school tutors can foster engaging and inclusive learning experiences.
On March 24-27, 2025, the e-Lite group will attend (in person) the 30th International Conference on Intelligent User Interfaces (IUI 2025) in Cagliari, Italy.
Tommaso Calò will present the paper "DeepFlow: A Flow-Based Visual Programming Tool for Deep Learning Development" on Thursday, March 27 during the Democratisation of AI session at 10:05 AM.
On September 4-6, 2024, the e-Lite group will attend (in person) the 4th International Conference on Information Technology for Social Good (GoodIT 2024) in Bremen, Germany. Luca Scibetta will present the work-in-progress paper "Dialogues with Digital Wisdom: Can LLMs Help Us Put Down the Phone?" on Wednesday, 4 September at 10:00 (WiP 1).
We are excited to announce the publication of our latest research paper in Personal and Ubiquitous Computing. The study, titled "Enhancing smart home interaction through multimodal command disambiguation," and conducted by me and Luigi De Russis, explores an innovative approach to making smart homes more intuitive and responsive to user commands.
On June 26, I presented the work "Empowering Users: End User Development for Mobile Applications Privacy Management" at the first International Workshop on Trusted Computing and Artificial Intelligence applied to Cybersecurity, held in Paris.
Smartphones have become integral to everyday life, offering numerous benefits but also raising significant privacy and security concerns. Users often face challenges managing app permissions and protecting personal data due to the complexity of existing smartphone operating system settings. Our research addresses these issues by introducing Privacy Manager, a mobile application designed for Android devices that employs an End-User Development (EUD) approach.
On June 2024, 2024, Luigi De Russis joined (online) the closing and awards ceremony at the Intelligent Environments (IE) 2024 conference to receive the Most Influential Paper Award for the 2018 paper entitled "'Hey Siri, do you understand me?': Virtual Assistants and Dysarthria".
On June 4-7, 2024, the e-Lite group will attend (in person) the 17th International Conference on Advanced Visual Interfaces (AVI 2024) in Arenzano, Italy.
The group will organize a workshop entitled "Digital Wellbeing for Teens: Designing Educational Systems (DIGI-Teens 2024)" in the morning of Tuesday, 4 June as part of a PRIN 2022 research project. Luigi De Russis, Alberto Monge Roffarello, Luca Scibetta e Massimiliano Pellegrino will join the workshop (and the entire conference).
Massimiliano Pellegrino will present the short paper "Digital Wellbeing Lens: Design Interfaces That Respect User Attention" on Friday, 7 June at 12:00 (session: Design).
People nowadays have access to Digital Self-Control Tools (DSCTs) that can help them manage their technology use. These tools offer features such as timers and the ability to disable distracting functionalities like recommendations and newsfeeds. However, researchers have identified several limitations with existing DSCTs, ranging from theoretical gaps to an overreliance on users' self-monitoring abilities.
In our work, we tried to overcome such limits and effectively support people in regaining control over smartphone use in the long term, focusing on teaching users how to relate better with technology, so that they can break unwanted smartphone habits and establish alternative behaviors without being forced to use a supportive tool forever.
Specifically, we designed, implemented, and evaluated StepByStep, a novel mobile DSCT that proactively assists users in learning how to regulate smartphone use.
By monitoring user's behavior, the app suggests new personalized learning paths composed of adaptable and continuously variable interventions to reduce and change unwanted behaviors with the smartphone. These paths can be at phone or app-level, and may be used to shape different behaviors, from avoiding using the smartphone in specific circumstances to using an app for an established amount of time. The main idea behind a learning path, in particular, is to progressively reduce the degree of support of the tool - i.e., the intensity of the associated intervention - based on user's achievements, until the user acquires a sufficient level of independence, i.e., it is able to sustain the new behavior without the help of the tool. To this end, StepByStep follows a gamification approach through which the intensity of an intervention is divided into four different levels. Users can gain points and advance in levels, i.e., by receiving less support, if they consistently respect the intervention with its current intensity for a sufficient amount of time. However, they can also lose points and downgrade to previous levels, i.e., by receiving more support, if they consistently fail to respect the intervention with its current intensity.