publications

2023

1. SNAM

   Constrained Expectation-Maximisation for inference of social graphs explaining online user-user interactions

   Effrosyni Papanastasiou, and Anastasios Giovanidis

   Journal of Social Network Analysis and Mining (Springer), 2023

   Abs Bib HTML PDF

   Current network inference algorithms fail to generate graphs with edges that can explain whole sequences of node interactions in a given dataset or trace. To quantify how well an inferred graph can explain a trace, we introduce feasibility, a novel quality criterion, and suggest that it is linked to the result’s accuracy. In addition, we propose CEM-*, a network inference method that guarantees 100% feasibility given online social media traces, which is a non-trivial extension of the Expectation-Maximization algorithm developed by Newman (2018). We propose a set of linear optimization updates that incorporate a set of auxiliary variables and a set of feasibility constraints; the latter takes into consideration all the hidden paths that are possible between users based on their timestamps of interaction and guide the inference toward feasibility. We provide two CEM-* variations, that assume either an Erdos Renyi (ER) or a Stochastic Block Model (SBM) prior for the underlying graph’s unknown distribution. Extensive experiments on one synthetic and one real-world Twitter dataset show that for both priors CEM-* can generate a posterior distribution of graphs that explains the whole trace while being closer to the ground truth. As an additional benefit, the use of the SBM prior infers and clusters users simultaneously during optimization. CEM-* outperforms baseline and state-of-the-art methods in terms of feasibility, run-time, and precision of the inferred graph and communities. Finally, we propose a heuristic to adapt the inference to lower feasibility requirements and show how it can affect the precision of the result.

   @article{SNAM.230110646,
     title = {Constrained Expectation-Maximisation for inference of social graphs explaining online user-user interactions},
     author = {Papanastasiou, Effrosyni and Giovanidis, Anastasios},
     numpages = {20},
     journal = {Journal of Social Network Analysis and Mining (Springer)},
     year = {2023},
     publisher = {Springer},
     doi = {2301.10646},
     dimensions = {true},
   }

2. ComplexN

   Opening up echo chambers via optimal content recommendation

   Antoine Vendeville, Anastasios Giovanidis, Effrosyni Papanastasiou, and 1 more author

   Complex Networks and Their Applications XI: Proceedings of The Eleventh International Conference on Complex Networks and Their Applications: COMPLEX NETWORKS 2022—Volume 1, 2023

   Abs Bib HTML PDF

   Online social platforms have become central in the political debate. In this context, the existence of echo chambers is a prob- lem of primary relevance. These clusters of like-minded individuals tend to reinforce prior beliefs, elicit animosity towards others and aggravate the spread of misinformation. We study this phenomenon on a Twitter dataset related to the 2017 French presidential elections and propose a method to tackle it with content recommendations. We use a quadratic program to find optimal recommendations that maximise the diversity of content users are exposed to, while still accounting for their preferences. Our method relies on a theoretical model that can sufficiently describe how content flows through the platform. We show that the model pro- vides good approximations of empirical measures and demonstrate the effectiveness of the optimisation algorithm at mitigating the echo cham- ber effect on this dataset, even with limited budget for recommendations.

   @article{2206.03859,
     title = {Opening up echo chambers via optimal content recommendation},
     author = {Vendeville, Antoine and Giovanidis, Anastasios and Papanastasiou, Effrosyni and Guedj, Benjamin},
     numpages = {12},
     journal = {Complex Networks and Their Applications XI: Proceedings of The Eleventh International Conference on Complex Networks and Their Applications: COMPLEX NETWORKS 2022—Volume 1},
     year = {2023},
     publisher = {Springer},
     doi = {2206.03859},
     url = {https://link.springer.com/chapter/10.1007/978-3-031-21127-0_7},
     dimensions = {true}
   }

2022

1. CCS2022

   Recommendation of content to mitigate the echo chamber effect

   Antoine Vendeville, Anastasios Giovanidis, Effrosyni Papanastasiou, and 1 more author

   Conference on Complex Systems, Palma de Mallorca, Spain, 2022

   Bib HTML

   @article{hal04010528,
     title = {Recommendation of content to mitigate the echo chamber effect},
     author = {Vendeville, Antoine and Giovanidis, Anastasios and Papanastasiou, Effrosyni and Guedj, Benjamin},
     url = {https://hal.science/hal-04010528},
     journal = {{Conference on Complex Systems, Palma de Mallorca, Spain}},
     year = {2022},
   }

2021

1. ASONAM

   Bayesian Inference of a Social Graph with Trace Feasibility Guarantees

   Effrosyni Papanastasiou, and Anastasios Giovanidis

   ASONAM ’21: Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, 2021

   Abs Bib HTML PDF

   Network inference is the process of deciding what is the true unknown graph underlying a set of interactions between nodes. There is a vast literature on the subject, but most known methods have an important drawback: the inferred graph is not guaranteed to explain every interaction from the input trace. We consider this an important issue since such inferred graph cannot be used as input for applications that require a reliable estimate of the true graph. On the other hand, a graph having trace feasibility guarantees can help us better understand the true (hidden) interactions that may have taken place between nodes of interest. The inference of such graph is the goal of this paper. Firstly, given an activity log from a social network, we introduce a set of constraints that take into consideration all the hidden paths that are possible between the nodes of the trace, given their timestamps of interaction. Then, we develop a nontrivial modification of the Expectation-Maximization algorithm by Newman [1], that we call Constrained-EM, which incorporates the constraints and a set of auxiliary variables into the inference process to guide it towards the feasibility of the trace. Experimental results on real-world data from Twitter confirm that Constrained-EM generates a posterior distribution of graphs that explains all the events observed in the trace while presenting the desired properties of a scale-free, small-world graph. Our method also outperforms established methods in terms of feasibility and quality of the inferred graph.

   @article{3487351.3488279,
     title = {Bayesian Inference of a Social Graph with Trace Feasibility Guarantees},
     author = {Papanastasiou, Effrosyni and Giovanidis, Anastasios},
     journal = {ASONAM '21: Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining},
     year = {2021},
     publisher = {IEEE/ACM},
     doi = {10.1145/3487351.3488279},
     url = {https://dl.acm.org/doi/abs/10.1145/3487351.3488279},
     dimensions = {true}
   }

2019

1. SIGIR

   Tensor Factorization with Label Information for Fake News Detection

   Frosso Papanastasiou, Georgios Katsimpras, and Georgios Paliouras

   ASONAM ’21: Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, 2019

   Abs Bib HTML PDF

   The buzz over the so-called "fake news" has created concerns about a degenerated media environment and led to the need for technological solutions. As the detection of fake news is increasingly considered a technological problem, it has attracted considerable research. Most of these studies primarily focus on utilizing information extracted from textual news content. In contrast, we focus on detecting fake news solely based on structural information of social networks. We suggest that the underlying network connections of users that share fake news are discriminative enough to support the detection of fake news. Thereupon, we model each post as a network of friendship interactions and represent a collection of posts as a multidimensional tensor. Taking into account the available labeled data, we propose a tensor factorization method which associates the class labels of data samples with their latent representations. Specifically, we combine a classification error term with the standard factorization in a unified optimization process. Results on real-world datasets demonstrate that our proposed method is competitive against state-of-the-art methods by implementing an arguably simpler approach.

   @article{1908.03957,
     title = {Tensor Factorization with Label Information for Fake News Detection},
     author = {Papanastasiou, Frosso and Katsimpras, Georgios and Paliouras, Georgios},
     numpages = {7},
     journal = {ASONAM '21: Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining},
     year = {2019},
     doi = {10.48550/arXiv.1908.03957},
     url = {https://doi.org/10.48550/arXiv.1908.03957},
     dimensions = {true}
   }

2. VR

   Virtual and augmented reality effects on K-12, higher and tertiary education students’ twenty-first century skills

   George Papanastasiou, Athanasios Drigas, Charalabos Skianis, and 2 more authors

   Virtual Reality, Springer London, 2019

   Abs Bib HTML

   The purpose of this review article is to present state-of-the-art approaches and examples of virtual reality/augmented reality (VR/AR) systems, applications and experiences which improve student learning and the generalization of skills to the real world. Thus, we provide a brief, representative and non-exhaustive review of the current research studies, in order to examine the effects, as well as the impact of VR/AR technologies on K-12, higher and tertiary education students’ twenty-first century skills and their overall learning. According to the literature, there are promising results indicating that VR/AR environments improve learning outcomes and present numerous advantages of investing time and financial resources in K-12, higher and tertiary educational settings. Technological tools such as VR/AR improve digital-age literacy, creative thinking, communication, collaboration and problem solving ability, which constitute the so-called twenty-first century skills, necessary to transform information rather than just receive it. VR/AR enhances traditional curricula in order to enable diverse learning needs of students. Research and development relative to VR/AR technology is focused on a whole ecosystem around smart phones, including applications and educational content, games and social networks, creating immersive three-dimensional spatial experiences addressing new ways of human–computer interaction. Raising the level of engagement, promoting self-learning, enabling multi-sensory learning, enhancing spatial ability, confidence and enjoyment, promoting student-centered technology, combination of virtual and real objects in a real setting and decreasing cognitive load are some of the pedagogical advantages discussed. Additionally, implications of a growing VR/AR industry investment in educational sector are provided. It can be concluded that despite the fact that there are various barriers and challenges in front of the adoption of virtual reality on educational practices, VR/AR applications provide an effective tool to enhance learning and memory, as they provide immersed multimodal environments enriched by multiple sensory features.

   @article{VR19PAP,
     title = {Virtual and augmented reality effects on K-12, higher and tertiary education students’ twenty-first century skills},
     author = {Papanastasiou, George and Drigas, Athanasios and Skianis, Charalabos and Lytras, Miltiadis and Papanastasiou, Effrosyni},
     journal = {Virtual Reality, Springer London},
     year = {2019},
     doi = {10.1007/s10055-018-0363-2},
     url = {https://doi.org/10.1007/s10055-018-0363-2},
   }

2018