[ 921INSYLUDK13 ] KV Learning from User-generated Data

Workload Education level Study areas Responsible person Hours per week Coordinating university
4,5 ECTS M1 - Master's programme 1. year Computer Science Markus Schedl 3 hpw Johannes Kepler University Linz
Detailed information
Original study plan Master's programme Computer Science 2021S
Objectives This course enables students to understand and apply basic methods for acquiring and mining user-generated data, in particular through machine learning technology. Students further obtain a solid knowledge of algorithms to build recommender systems that work with different kinds of user-generated data sources (e.g., multimedia content descriptors and user-item interactions). At the end of the course, students will be capable of

  • applying and devising methods to leverage data on explicit and implicit user-item interactions/feedback
  • applying and devising methods to extract content descriptors from user-generated items
  • creating a collaborative filtering recommender system
  • creating a content-based recommender systems
  • deciding on suited hybridization approaches to combine different recommender system algorithms
  • making informed decisions about evaluation strategies for recommender systems
Subject The subject matters covered in this course include sources of user-generated data, methods to acquire and analyze web and social media data, and methods to mine user behavior and feedback data (explicit and implicit). Strong emphasis is further given to the use of this kind of data to build recommender systems (user preference learning), adopting the techniques of collaborative filtering, content-based filtering, and hybridization.

The lecture is accompanied by practical exercises in which students carry out several tasks to mine and analyze user-generated data, and to implement various recommender system algorithms.

Criteria for evaluation written exam, practical exercises
Methods lectures, practical exercises
Language English
Study material slides, scientific papers
Changing subject? No
On-site course
Maximum number of participants -
Assignment procedure Direct assignment