The DEPLATFORM project addresses a critical paradox of modern media digitization: while the real-time accessibility of news on social networks offers immense advantages, it also creates severe societal risks through the rise of agents that manufacture and spread online misinformation. To combat this, DEPLATFORM aims to empower social media users to separate truth from falsehood by developing an intelligent, interactive system dedicated to detecting the veracity of news published online.
Advanced Veracity Detection: To develop novel ensemble deep neural network models that significantly improve fake news detection by simultaneously analyzing diverse textual features and information diffusion graphs.
Network Immunization: To design and implement innovative social network immunization strategies capable of actively halting the spread of misinformation online.
By moving beyond passive detection into active containment, DEPLATFORM will offer a vital defense mechanism for democratic processes, reduce ideological polarization, and equip the public with an actionable tool to combat digital deception.
Ciprian-Octavian Truică, Elena-Simona Apostol, Marius Marogel, Adrian Paschke. GETAE: Graph Information Enhanced Deep Neural NeTwork Ensemble. Expert Systems with Applications, 275:1-14(126984), ISSN 0957-4174, May 2025, DOI: 10.1016/j.eswa.2025.126984 (Q1 Journal) [pdf]
Elena-Simona Apostol, Ciprian-Octavian Truică, Adrian Paschke.ContCommRTD: A Distributed Content-Based Misinformation-Aware Community Detection System for Real-Time Disaster Reporting. IEEE Transactions on Knowledge and Data Engineering, 36(11):5811-5822, ISSN: 1041-4347, November 2024, DOI: 10.1109/TKDE.2024.3417232 (Q1 Journal) [pdf]
Dagmar Gromann, Elena-Simona Apostol, Christian Chiarcos, Marco Cremaschi, Jorge Gracia, Katerina Gkirtzou, Chaya Liebeskind, Liudmila Mockiene, Michael Rosner, Ineke Schuurman, Gilles Sérasset, Purificação Silvano, Blerina Spahiu, Andrius Utka, Ciprian-Octavian Truică, Giedrė Valūnaitė Oleškevičienė. Multilinguality and LLOD: A Survey Across Linguistic Description Levels. Semantic Web Journal, 15(5):1915-1958 ISSN 1570-0844, October 2024. DOI: 10.3233/SW-243591 (Q2 Journal) [pdf]