Maria Eleni Vardaki
Maria Eleni Vardaki owns a Bachelor's Degree from the Department of Journalism and Mass Communication (Aristotle University of Thessaloniki) and a master's in Digital Communication Media and Interaction Environments (National and Kapodistrian University of Athens). Since 2011 she works for the Hellenic Police in Greece, while from 2015 she performs duties in the Press Office. She has previous experience in the private sector in Telecommunications Systems and Internal and External Communication of PPC S.A. With her thesis, she introduces the power of Artificial Intelligence in combination with Big Data in the fight against crime.
Catherine Sotirakou is a Ph.D. candidate in the field of computational journalism at the University of Athens, she holds a master’s in digital media and interactive environments (UoA) and a bachelor’s in journalism (AUTH). She worked for 6 years as a broadcast journalist at Alpha TV, and in 2017 she was awarded a Stavros Niarchos scholarship to study in the Lede Program at Columbia University in the city of New York. After that, she worked as a Tech and Innovation Consultant at Alpha TV and she was responsible for the digital transformation of the television channel. Her project won 3 awards: 2 Ermis Awards (Silver – Content Website, Bronze – UI & Usability) & 1 DIME Award (Gold – Best Responsive or Mobile Edition). Her main research interests are AI for measuring quality in digital news stories, data journalism, audience analysis, and natural language processing.
Constantinos Mourlas is an Associate Professor in the Faculty of Communication and Media Studies, National and Kapodistrian University of Athens (Greece) since 2002. He graduated from the University of Crete in 1988 with a Diploma in Computer Science and obtained his Ph.D. from the Department of Informatics, University of Athens in 1995. Dr. C. Mourlas joined the Department of Computer Science of the University of Cyprus in 1997 as a visiting Assistant Professor and as Lecturer in the same Department from 1999 to 2002. In 1998 was an ERCIM fellow for post-doctoral studies through research. He has participated in National and European projects such as :
• CALYPSO - Collaborative AnaLYsis, and exPosure of diSinfOrmation, European Project Connect/2020/5464403, 2021 -2022.
• iQJournalism: An Intelligent Advisor Predicting Perceived Quality in Journalism, National Project (ESPA), 2021 – 2023.
• FACT-CHECKING European cooperation project on disinformation and fact-checking training. Empowering current and future media and media education professionals, to identify, prevent, and combat fake news spread over digital networks, Erasmus+ KA2, Sept. 2019 - Aug.2022.
• Creative Europe Project "LABOURGAMES", Ref N°: 570569-CREA-1-2016-1-DE-CULT-COOP1, Creative Europe - Culture Sub– Support to European cooperation projects – 2016 – 2019.
• Play2DO - A simulated training framework for skills development addressing students with intellectual and developmental disabilities and their trainers. Reference no. 2016-1-UK01-KA202-024613, Erasmus+, 2016 – 2018.
• PredMine: A PREDICTIVE ANALYSIS PLATFORM USING LIVE BIG DATA, A Bilateral Cooperation of Science & Technology between Greece and Israel 2013-2015. Co-financed by Greece and the European Union - European Regional Development Fund.
• Erasmus+ European Project, M-CARE European Project (M-Care - 539913-LLP-1-2013-1-TR-LEONARDO-LMP), Duration: 2013-2015
• European Project Erasmus+ " Assistive Technology Learning Through A Unified Curriculum/ ATLEC", LEONARDO DA VINCI Multilateral Projects for Development of innovation (duration: 1/1/2012 - 31/12/2014, total budget: 533.288 euros).
• Code RED, UK/13/LLP-LdV/TOI-678, Type: LLP-Leonardo-Transfer of Innovation, Starting date: 01 Oct 2013, Duration: 24 months
• RECALL - Reconnecting Excluded Communities via Lifelong Learning through the Use of Location-Based Services (RECALL KA3 LLL project - 504970-LLP-1-2009-1-UK-KA3-KA3MP) (duration: 1/11/2009 - 31/12/2012, total budget: 589.000 euros)
Current main research interests: The design and the development of communication environments that provide adaptive and personalized context to the users according to their needs, preferences, cognitive characteristics, and emotional state. Also, the use of AI in measuring quality journalism and political communication ideologies.
Sessions
Nowadays police authorities, implement computational techniques like machine learning algorithms to forecast criminal details such as crime scenes, or personal characteristics of potential perpetrators. In Greece however, Artificial Intelligence and its potential are not widely explored. In this paper, we collected unstructured data from press releases of the Hellenic Police from 2015 to 2020, and then we manually constructed the dataset. More specifically, variables like the time of the investigation of each case, the place of the arrest, along with nationality, age, type of the offense, and confiscated items were included in the dataset. In the case of a conflict between collected values, the press release in question was omitted from the data. Furthermore, we matched the place of the arrest with its corresponding postal code and added some key statistics from the Hellenic Statistical Authority, namely the population of each area, the marital status of those living in every neighborhood, and their employment (i.e. merchants, farmers, employees, retirees).
For the experiments, we used tree-based machine learning models from the NLTK Library to predict between different kinds of crime. We conducted two experiments using Python, the first aimed at classifying burglary, theft, and fraud and the second was a binary classification between burglary and theft. The training set consisted of 70% of the data and the rest 30% was used for testing, also the F1-score was implemented for the evaluation of the model. The findings showed that the binary classification produced better results, with the model being able to predict between burglary and theft with 75% accuracy. This is the first attempt to our knowledge that implements predictive models to forecast crime in Greece, and our results suggest that this is a promising approach that might assist in daily policing. We consider that our experiment would be a start for the Hellenic Police to know how to predict and analyze crime, starting from the data interpretation and ending with the algorithmic models.