HeyTAP^2 at work

In the Internet of Things, users are willing to personalize the joint behavior of their connected entities, i.e., smart devices and online service, by means of trigger-action rules such as "IF the entrance Nest security camera detects a movement, THEN blink the Philips Hue lamp in the kitchen." Unfortunately, the spread of new supported technologies make the number of possible combinations between triggers and actions continuously growing, thus motivating the need of assisting users in discovering new rules and functionality, e.g., through recommendation techniques.

The paper "From Users' Intentions to IF-THEN Rules in the Internet of Things", recently accepted by the ACM Transactions on Information Systems, introduces HeyTAP², a semantic Conversational Search and Recommendation (CSR) system able to suggest pertinent IF-THEN rules that can be easily deployed in different contexts starting from abstract users' needs.

By exploiting a conversational agent, the user can communicate her current personalization intention by specifying a set of functionality at a high level, e.g., to decrease the temperature of a room when she left it. Stemming from this input, HeyTAP² implements a semantic recommendation process that takes into account a) the current user’s intention, b) the connected entities owned by the user, and c) the user's long-term preferences revealed by her profile. If not satisfied with the suggestions, the user can converse with the system to provide further feedback, i.e., a short-term preference, thus allowing HeyTAP² to provide refined recommendations that better align with the her original intention.

Finally, HeyTAP² was evaluated by running different offline experiments with simulated users and real-world data. On the one hand, we tested the recommendation process in different configurations, and we show that recommendation accuracy and similarity with target items increase as the interaction between the algorithm and the user proceeds. On the other hand, we compared HeyTAP² with other similar baseline recommender systems. Results demonstrate the effectiveness of HeyTAP² in recommending IF-THEN rules that satisfy the current personalization intention of the user.

CHI 2021 logo

We are happy to announce that we have one full paper and a Late-Breaking Work (LBW) accepted at CHI 2021, the premier international conference of Human-Computer Interaction. ACM CHI 2021 will be held this week (May 8-13) online. Both the paper and the LBW are about digital wellbeing: the paper features our work on digital wellbeing in a multi-device setting, while the LBW introduces novel patterns for reducing risk in web-based digital self-control tools.

Luca Mannella

The e-Lite research group welcomes Luca Mannella, who started his Ph.D. in Computer and Control Engineering in the XXXVI cycle, on November 2020. Luca is co-advised by Fulvio Corno and Antonio Lioy, and will work on topics lying in the intersection of Internet of Things and Cybersecurity.

AVI 2020 logo

In this strange period, the e-Lite group will participate at the International Conference on Advanced Visual Interfaces (AVI 2020) in multiple ways and roles. AVI will be held at the Ischia Island (and eveywhere in the world, for online participants) from September 28 to October 2.

On Wednesday, July 15, 2020, at 10:00, Juan Pablo Sáenz will defend his Ph.D. final dissertation titled "Software Engineering in the IoT Context: Characteristics, challenges, and enabling strategies".

The defense will be evaluated by the international commission composed of: Juan Carlos Augusto (Middlesex University, UK), Ana María Bernardos (Universidad Politécnica de Madrid, ES), Maristella Matera (Politecnico di Milano, IT), and Giuliana Franceschinis (Università del Piemonte Orientale, IT); and will be coordinated by Marco Torchiano (Politecnico di Torino, IT).

The discussion will be on-line and is open to anyone interested.

Data4Good: Designing for Diversity and Development

The workshop "Data4Good: Designing for Diversity and Development", to be held on September 28th, 2020, at the Island of Ischia, Italy is currently accepting contributions!

An AVI 2020 workshop that aims at expanding the discussions on how appropriate human-centered design can contribute to addressing data-related challenges among marginalised and under-represented/underserved groups around the world.