CHRISTINA BOIDIDOU
Data Scientist
EDUCATION
Diploma in Electrical and Computer Engineering
Aristotle University of Thessaloniki, School of Computer and Electrical Engineering, Department of Electronics and Computer Engineering / 2006 - 2013
Thesis: A linguistic analysis for identifying quality attributes on reports from Software Repositories.
Fields: Semantic Analysis, Natural Language Processing
Techniques and tools: Java, WEKA, Latent Dirichlet Allocation (LDA).
Fields: Semantic Analysis, Natural Language Processing
Techniques and tools: Java, WEKA, Latent Dirichlet Allocation (LDA).
WORKING EXPERIENCE
Research Data Scientist
Urban Big Data Centre, Glasgow, UK
/ August 2017 - Present
Perform data exploration and analysis
Apply data mining and machine learning techniques to extract information
Python (pandas, scikit-learn, pytorch)
Apply data mining and machine learning techniques to extract information
Python (pandas, scikit-learn, pytorch)
Back-end and Data Developer
ICAN Future Star Ltd, Glasgow, UK
/ November 2016 - July 2017
Develop and evaluate the back-end of an application that suggests Courses and Universities to prospective students based on their profile.
REST API development
Natural Language Processing for detecting text duplicates
Database management
Data crawling and retrieval, data exploration and analysis.
Python (flask, elasticsearch,pandas, numpy)
ElasticSearch, DynamoDB databases
GIT tools
REST API development
Natural Language Processing for detecting text duplicates
Database management
Data crawling and retrieval, data exploration and analysis.
Python (flask, elasticsearch,pandas, numpy)
ElasticSearch, DynamoDB databases
GIT tools
Research Assistant
Centre of Research & Technology - Hellas/Information Technologies Institute (CERTH/ITI)
/ July 2013 - October 2016
Develop and evaluate a computational verification framework (Fake Post Detector at Github) to predict fake user-generated content spread on Twitter.
Dataset organization and enrichment used for the verification framework, data visualizations.
Feature extraction and engineering.
Experimentation with different approaches, such as various types of classifiers, classifiers fusion and feature selection.
Organization of the Verifying Multimedia Use task in the context of MediaEval 2015 Workshop.
Java (WEKA software for ML, Eclipse, maven, Spring framework)
Python (pandas, scikit-learn, seaborn, matplotlib, selenium, pymongo packages)
Basic NLP techniques for text-based features’ extraction (pattern matching, regex, Levenshtein distance)
NoSQL (MongoDB) for data storage
Decision trees (J48, Random Forest), Linear Regression
Dataset organization and enrichment used for the verification framework, data visualizations.
Feature extraction and engineering.
Experimentation with different approaches, such as various types of classifiers, classifiers fusion and feature selection.
Organization of the Verifying Multimedia Use task in the context of MediaEval 2015 Workshop.
Java (WEKA software for ML, Eclipse, maven, Spring framework)
Python (pandas, scikit-learn, seaborn, matplotlib, selenium, pymongo packages)
Basic NLP techniques for text-based features’ extraction (pattern matching, regex, Levenshtein distance)
NoSQL (MongoDB) for data storage
Decision trees (J48, Random Forest), Linear Regression
PUBLICATIONS
C.Boididou, S. Papadopoulos, L. Apostolidis and Y. Kompatsiaris, Learning to Detect Misleading Content on Twitter, ICMR 2017, ACM International Conference on Multimedia Retrieval (2017)
C. Boididou, S. Papadopoulos, Y. Kompatsiaris, S. Schifferes, N. Newman. Challenges of computational verification in social multimedia. In Proceedings of the companion publication of the 23rd intern. Conference on World Wide Web companion (WWW Companion '14), 743-748 (2014)
C. Boididou, K. Andreadou, S. Papadopoulos, D. Dang-Nguyen, G. Boato, M. Riegler, and Y. Kompatsiaris. Verifying Multimedia Use at MediaEval 2015. In proceedings of the MediaEval 2015 Workshop, Sept. 14-15, 2015, Wurzen, Germany (2015)
C. Boididou, S. Papadopoulos, D. Dang-Nguyen, G. Boato, M. Riegler, and Y. Kompatsiaris. The CERTH-UNITN Participation @ Verifying Multimedia Use 2015. In proceedings of the MediaEval 2015 Workshop, Sept. 14-15, 2015, Wurzen, Germany (2015).