Recent & Upcoming Talks | Antonela Tommasel

Recommender systems and misinformation: What can we do about them?

Tue, 20 Sep 2022 14:00:00 +0000

Abstract

In recent years, social media has profoundly changed how people consume information to the extent that it arises as one of the primary news sources. One of the most valuable features of social platforms is their potential to propagate information on a large scale. However, the unmoderated nature of social media sites and the potential for automation and fast propagation make it easy for users to share inaccurate or intentionally misleading information, thus threatening access to reliable and trustworthy information. As mediators of online information consumption, recommenders are affected by the proliferation of low-quality and unwanted content, serving as an unintended means for their spread and massive amplification while reducing the quality of predictions. Recently, recommenders have undergone fairness criticism for inducing the creation of filter bubbles, echo chambers, and facilitating opinion manipulation. Similarly, users’ vulnerability to dis/misinformation can be fostered by data, algorithms, and interaction biases, which limit users’ openness to contrasting points of view. In this talk, we will explore different aspects related to how misinformation and recommender systems interrelate and how we can tackle that interrelation.

From Smart Cities to Social Cities: Smart Cities at the Service of Social Good

Wed, 28 Oct 2020 14:00:00 +0000

Abstract

“Today, 55 percent of the world’s population lives in urban areas, a proportion that is expected to increase to 68 percent by 2050.” – United Nations

Artificial intelligence has the potential to help improving many aspects of the daily life. In this context, making cities smarter is the challenge of the new era, which brings together aspects of computer sciences, physics, operations research, management science, decision sciences, economics and the social sciences. With the large amount of data available from diverse sources and the advance in technology, new opportunities to address the fundamental (and perhaps social) problems of cities, citizens and society arise. But this is not an individual effort. The more cities that are working toward the greater good, the more prosperous cities and citizens will be as a whole. In this talk we will explore how the data harnessed from cities can be applied to the social good. Then, we will focus on good practices for developing our solutions.

Surviving to social media in the misinformation era

Sat, 13 Jun 2020 14:00:00 +0000

Abstract

Social media has become the primary source of news for their users by enriching the life and activities of its users, thus giving rise to new forms of communication and interaction. Besides fostering social connections between their users, social media also represents the ideal environment for undesirable phenomena, such as the dissemination of unwanted or aggressive content, misinformation and fake news, which affect the individuals as well as the society as a whole. Thereby, in the last few years, the research on misinformation has received increasing attention. The unlimited possibilities offered by social media sites generate new problems related to information overload, the quality of published information and the formation of new social relationships. This opens the possibility to the contamination of social media with unwanted and unreliable content (false news, rumours, spam, hoaxes), which influences the perception and understanding of events, exposing users to risks. Motivated by the large amount of heterogeneous information available on social media and considering the consequences of the exposure to unwanted and unreliable content, the existence of accounts dedicated to sharing said content, and the rapid dispersion of both phenomena, in this talk we will explore the current actions that are being taken, and how simple processes as recommendations can affect misinformation diffusion. Then, we will focus on what is left to do and can we do to make social media a safer environment.

Keeping one-step ahead of Architectural Smells: A Machine Learning application

Wed, 02 Oct 2019 14:00:00 +0000

Abstract

Software systems naturally evolve, and this evolution often brings design problems that cause system degradation. Architectural smells are typical symptoms of such problems, and several of these smells are related to undesired dependencies among modules. The early detection of these smells is important for developers, so they can plan ahead for maintenance or refactoring efforts, thus preventing system degradation. Social Network Analysis (SNA) refers to a strategy for investigating social structures using network and graph theories. The link prediction problem adapts SNA techniques for studying to what extent the evolution of a network can be modelled by using features intrinsic to the network. Since the module structure can be regarded as a network, i.e., a dependency graph, we can leverage on network features to analyse the dynamics of such structure. In this talk, we will explore how link prediction and machine learning techniques could help anticipate architectural smells in future system versions. We will start with the basics of predicting future dependencies, up to the application of time forecasting and machine learning models for predicting the appearance of new architectural smells. Particularly, we will focus on two well-known dependency-related smells, cyclic dependencies and hub-like dependency. Finally, we will discuss some open issues and potential extensions.

Friends or Foe: Recommending friends in the misinformation era

Thu, 06 Jun 2019 14:00:00 +0000

Abstract

Social media has become the primary source of news for their users by enriching the life and activities of its users, thus giving rise to new forms of communication and interaction. Besides fostering social connections between their users, social media also represents the ideal environment for undesirable phenomena, such as the dissemination of unwanted or aggressive content, misinformation and fake news, which affect the individuals as well as the society as a whole. Thereby, in the last few years, the research on misinformation has received increasing attention. The unlimited possibilities offered by social media sites generate new problems related to information overload, the quality of published information and the formation of new social relationships. This opens the possibility to the contamination of social media with unwanted and unreliable content (false news, rumours, spam, hoaxes), which influences the perception and understanding of events, exposing users to risks. Motivated by the large amount of heterogeneous information available on the social Web and considering the consequences of the exposure to unwanted and unreliable content on social media, the existence of accounts dedicated to sharing said content, and the rapid dispersion of both phenomena, the goal of this work in progress is the provision of reliable recommendation systems based on the integration of techniques that automatically allow the detection of unreliable content and the users publishing it. Thereby, in this talk we will explore the concept of user trustworthiness to avoid making “bad” recommendations that could favour the propagation of unreliable content and polluting users. Then, we will focus on how could we model the behaviour of users and their social groups in the context of the information diffusion process. Finally, we will talk about the planned actions and research milestones.

Keeping one-step ahead of Architectural Smells: A Machine Learning application

Thu, 06 Sep 2018 14:00:00 +0000