Anno accademico 2020-2021


Carlo Tasso
Totale crediti: 6
Tipologia: Caratterizzante
Periodo didattico: Primo Periodo
Lingua insegnamento: INGLESE
Prerequisiti. The student should have knowledge about: basic techniques of Artificial Intelligence and Machine Learning, Software Engineering and Data Bases.
Metodi didattici. The course includes: lectures, exercises, laboratories and seminars.
Modalità di verifica. In the initial weeks of the course, specific Project Works will be assigned to the students. These assignements will possibly include limited software development tasks and/or alternatively the study of some specific topic and the subsequent presentation of a seminar. Project work has to be completed by the end of the course. An oral examination on some specific topic included in the lectures can be required.


The course objectives are:

– Knowing basic concepts and algorithms ofrecommender systems, adaptive personalization techniques and user modeling;

– Understanding the relationship between Web personalization and the evolution of Web and Internet

– Knowing how to specify and to design a user model

– Knowing how to select the most adequate personalization techniques for a recommender system;

– Knowing how to analyze a personalized information access problem and how to propose a solution


The student will have to:

1. Knowledge and understanding: acquiring specific knowledge of the main concepts and basic principles of Recommender Systems and Web Content Personalization. Knowing and exploiting techniques for adaptive personalization.

2. Ability to apply knowledge and understanding: knowing how to analyze and interpret an adaptive personalization algorithm, how to analyze an information access problem, how to apply the above mentioned knowledge in specific Recommender System application context, how to design the logical architecture of a recommender system. Using a programming library (API) for developing recommender system modules.


The student will have to:

1. Autonomy of judgment: being able to independently evaluate the characteristics of the tools and methodologies to be applied in the various contexts of recommender and adaptive personalization systems.

2. Communicative skills: acquiring the ability to describe effectively and through appropriate models the scenario of an adaptive personalized recommender system, its benefits and risks

3. Learning skills: being able to learn the overall functioning of recommender systems and their implications.


The course introduces the basic concepts, principles, and techniques of Recommender Systems and personalization techniques, i.e. the software systems capable of adapting their behaviour to the specific individual user. The course aims at understanding the main problems arising during the design of a Recommender System and at knowing which software applications can benefit from adaptive recommender systems.

Specific Contents are: basic topics and definitions of Recommender Systems and Web Content Personalization; information access systems; User Modeling, Personalization Techniques (user tracking, web usage mininf, cognitive filtering, collaborative filtering, knowledge-based filtering, machine learning techniques for personalization, web usage mining, latent semantic indexing, singular value decomposition for dimensionality reduction); Application of Personalization Techniques to Recommender Systems; eveluation techniques for recommender systems.


Carlo Tasso, Paolo Omero, La Personalizzazione dei Contenuti Web – e-commerce, i-access, e-government, Franco Angeli, Milano, 2002.

Peter Brusilowsly, Alfred Kobsa, Wolfgang Nejdl (Eds.) The Adaptive Web – Methodes and Strategies of Web Personalization. Lecture Notes in Computer Science LNCS 4321. Springer Berlin Heidelberg, 2007.

Dietmar Jannach, Alexander Felfernig, Markus Zanker, Gerhard Friedrich, Recommender Systems: An Introduction, Cambridge University Press, Cambridge, 2010.

Giovanni Guida, Carlo Tasso, Design and Development of Knowledge-Based Systems – From Life Cycle to Methodology, John Wiley& Sons, Chichester, UK, 1994.

Charu C. Aggarwal, Recommender Systems, Springer, Switzerland, 2016.

Deepak K. Agarwal, Bee-Chung Chen, Statistical Method for Recommender Systems, Cambridge University Press, Cambridge, 2016.

Ricci F. et al. (Eds), Recommender Systems Handbook, Switzerland, 2011.