Michael Mäs

What can social-influence models teach us about the design of personalized recommender systems?
ECCAI talk

Personalization dramatically changed the Internet. Search engines provide results tailored to the interests of each individual user. Online markets recommend products based on the purchases of other customers who bought similar products in the past. Social networks rank incoming messages according to users’ interests. Personalization is of great help for users and is a multibillion-dollar business area. However, pundits warn that personalization creates cocoons of like-minded users, which makes the Internet boring and uninspiring.
More worryingly, however, it has been warned that exposing users to ideas, news, and information that support their views will reinforce their opinions and, thus, foster the polarization of political opinions. These warnings received increasing attention, as opinion polarization might endanger societal cohesion and pose a challenge for political decision-making, as it impedes political consensus formation also on non-controversial issues.
Reviewing the literature on social influence in networks and the conditions of opinion polarization, I will demonstrate in this talk that state-of-the art theory leaves us with great uncertainty about the consequences of personalization. In fact, two highly accepted models of opinion dynamics make opposing predictions about the consequences of personalization: Persuasion models, on the one hand, predict that personalization will increase polarization. Rejection models, on the other hand, imply that personalization will foster consensus rather than polarization. There is, thus, a pressing need to clarify which model better captures the effects of personalization.
Second, I will describe the design of controlled experiments conducted on online social networks that allow calibrating the agents of existing influence models, which will make it possible to derive reliable predictions about the consequences of web personalization.
Third, I will discuss implications of social-influence models for the development of personalized recommender systems. I will sketch different approaches to developing systems that generate personalized outcomes without fostering opinion polarization. I will show that such systems cannot be developed without an accurate model of social influence.
On a more general level, I will conclude that the development of technologies on the Internet that have the potential to affect societal dynamics should be guided by theoretical and empirical research. In models of complex systems, even small and seemingly innocent differences in the assumptions about the underlying micro-mechanisms can have critical effects on macro-outcomes. As information technology affects micro-mechanisms, it crucial to understand possible consequences before it is too late to intervene.


Franco Zambonelli

Coordination in Urban-scale Heterogeneous Multiagent Systems
Most of the emerging scenarios in the area of software-intensive systems and smart cities involve a very large number of interacting autonomous components (i.e., agents). In my talk, I argue that the peculiar features of such emerging multiagent systems (up to millions of interacting components, geographically-distributed over vast areas, mixing humans and artificial components, and lacking any form of central control) call for radically novel approaches to coordinate their overall activities and functionalities. In particular, during the talk, I will overview some representative scenarios of emerging large-scale multiagent systems in the area of urban computing, discuss the key challenges to be faced by research in coordination models and technologies, and eventually sketch some promising research directions.


Marc Cavazza

Brain-Computer Interfacing to Agents
Brain-Computer Interfaces (BCI) have attracted significant interest as an interaction technique, beyond their original potential for assistive technologies. While BCI are often seen as a low bandwidth input mechanism to control devices, they can also open a window on some high-level cognitive functions such as executive decision-making, risk taking and affective regulation. This is a consequence of the ability of BCI techniques to acquire signals from various areas of the brain, such as the prefrontal cortex.
In this talk, I will present recent and ongoing research exploring Brain-Computer Interfacing to agents, considering both virtual agents and rational agents. We have used several BCI techniques (EEG, fNIRS) to capture the activity of the prefrontal cortex in real-time, with a specific emphasis on measuring prefrontal cortex asymmetry. I will discuss how this type of BCI can be used in various agents systems, from communicating with Embodied Conversational Agents to influencing the behaviour of a heuristic search algorithm.
Finally, I will discuss the new perspectives that BCI research could bring to some popular topics in Agents research.