The Internet of tomorrow: Privacy, Accountability, Compliance and Trust

A provider-side mechanism to produce tangible explanations for end-users, where an explanation is defined to be a set of minimal actions performed by the user that, if removed, changes the recommendation to a different item.

A probabilistic graphical model to jointly identify credible news articles, trustworthy news sources, and expert users by leveraging joint interactions in a news community.

Assessing trustworthiness of users, objectivity of language, and credibility of user statements in online health communities.

Probabilistic graphical models to extract "credible", "trustworthy" and "expert" information from large-scale, non-expert, user-generated content in online communities.

A deep learning based approach for credibility analysis of unstructured textual claims in an open-domain setting with interpretable explanations.

A generic approach for credibility analysis of unstructured textual claims in an open-domain setting with interpretable explanations.

This project presents a ranking-based approach to the assessment of privacy risks emerging from textual contents in online communities, focusing on sensitive topics, such as being depressed.

This project introduces a method for probabilistically clustering user records into a low-rank representation that captures individual fairness yet also achieves high accuracy in classification and regression models.

This project proposes a framework which leverages solidarity in a large community to scramble user interaction histories.

This project presents FAIRY, a framework that systematically discovers, ranks, and explains relationships between users’ actions and items in their social media feeds.

A human-in-the-loop framework, called ELIXIR, where user feedback on explanations is leveraged for pairwise learning of user preferences.

Moving forward towards deriving more human understandable evidence from Knowledge graphs and text based on background knowledge in the form of rules.