Research team on Data & Web Mining

Latest News

  • Prof Vazirgiannis presents in the European Summer School in Information Retrieval (ESSIR) tutorial entitled "Graph-of-words: boosting text mining with graphs"

  • Παρουσίαση: Αρχειοθέτηση ιστοπεριεχομένου και διατήρηση ψηφιακής μνήμης: "η εμπειρία του ΟΠΑ"-Μ. Βαζιργιάννης, Επιστημονική Ημερίδα: Η συμβολή των οικονομικών βιβλιοθηκών στην έρευνα και στην ανάπτυξη, Τράπεζα της Ελλάδος, Παρασκευή 6 Μαρτίου 2015, Περισσότερα: εδώ.

  • Margarita Karkali defended successfully her PhD thesis “Efficient Novelty Detection in Document Streams” on 7/7/2014.


Knowledge Mining from Databases and the WWW (Fall Semester)
Course Objectives
  • Introduction in data analysis methods and algorithms along with the relevant software tools
  • Participation in data mining cups and contests
Course Content
  • Introduction to Data Mining, data preprocessing)
  • Non supervised Learning): Clustering, Association Rules)
  • Supervised learning: Classification Naive Bayes Classifier, K-nn
  • Web Mining: Web Crawling,Parsing, Web Archiving
  • Web adverstising, marketing.
  • Data pre-processing/feature selection and exploratory analysis with WEKA.
  • Clustering (k-means, ΕΜ)
  • Association rules
  • Classification (naive Bayes & decision trees)
  • Web Advertising Lab
Private leaderboard for data challenges

Our 2013 data mining class.

Machine Learning & Data Mining (Spring Semester)
Course Objectives
  • The dbnet aims to familiarize students with advanced methods of data mining and learning from data sets that are characterized by complexity and heterogeneity.
  • The machine learning algorithms are interesting solutions for modern problems such as assessing medical data for diagnosis, prediction, and detection of structure in biological and medical data, formulation of recommendations on websites, techniques for online advertising campaigns, etc.
Course Content
  • Supervised Learning: Prediction Techniques: Linear Regression, Model Selection, Generalized Linear Models, Support Vector Machines, Kernels
  • Unsupervised Learning: Gaussian Mixture Models, EM, Spectral Clustering, Dimensionality Reduction, Dynamical models (Markov Chains, HMMs, Kalman filters)
  • Preprocessing Methods: Feature Selection, Cross-validation, Bootstrapping, Semi-supervised learning, Active Learning
  • Case Studies: Web Mining, Internet Advertising, Proteomics
  • Regression and Introduction to Matlab Environment
  • Dimensionality Reduction
  • Feature Selection and Cross-Validation
  • Support Vector Machines
  • Clustering and Spectral Clustering