The document proposes fuzzy information filters (FIFs) to model users and resources for collective intelligence systems. FIFs can represent preferences and other attributes as fuzzy sets to handle gradual and imprecise information. A FIF structure models a user's preferences as filters that are composed sequentially and in parallel. FIFs can be learned over time from a user's observations to adapt the user model. The approach aims to provide personalized experiences through information filtering in applications like recommender systems.
1. corrado.mencar@uniba.it
Fuzzy Information Filters for User Modeling
in Collective Intelligence Systems
G. Castellano, C. Castiello, A.M. Fanelli, M. Lucarelli, C. Mencar
Dept. of Informatics, University of Bari, Italy
2. corrado.mencar@uniba.it
Research outline
↠ Purpose Define an abstract model for
representing users and resources
↠ Approach Fuzzy Information Filters (FIF).
↠ Values Generality, adaptivity, handling imprecise
information, explainability
↠ Impact personalized e-learning systems,
recommendation systems, community discovery,
etc.
3. corrado.mencar@uniba.it
Collective Intelligence
↠ Intelligence emerging from the interaction of
many individuals
→ collaboration, competition, opinions, messaging, …
↠ Personalized experience in web applications
↠ Information filtering
→ Based on data
→ Based on a model
4. corrado.mencar@uniba.it
Information filtering
↠ Fight information overload
→ the difficulty a person can have in
making decisions caused by too much
information. (Wikipedia)
↠ Deliver only relevant
information
→ User model
6. corrado.mencar@uniba.it
Graduality & Granularity
↠ Preferences & co. are always expressed to a
degree
→ Ranking of objects according to prefs., needs, etc.
↠ Preferences & co. are often imprecise
→ Refer to classes of objects instead of single individuals
11. corrado.mencar@uniba.it
Description-based filter
↠ An object is represented as a collection of
metadata
↠ Each metadata is defined by an attribute and a
fuzzy set of values
↠ A description-based filter is defined by an
attribute and a fuzzy set of values
13. corrado.mencar@uniba.it
User model as FIF structure
O
W
A
(Simplified diagram: not all lines are drawn)
O
W
A
User likes cheap, lightweight, small cars which have a low-consumption engine and 4-5 doors
15. corrado.mencar@uniba.it
Filter learning
↠ Filters can be designed by hand, or
↠ they could be acquired from past observations
→ sequence of objects observed by a user
↠ Theory of Possibility →
Principle of Minimum Specificity
I know John is a tall man (more than about
180cm) ⊢ Now I know John is within about
180-190 cmYou tell me John is not so tall (less than about
190cm)
16. corrado.mencar@uniba.it
Learning principles
↠ Temporal Locality. If I observe an object, I will observe
the same object in the near future
↠ Spatial Locality. If I observe an object, I will observe a
similar object
↠ Relevance of knowledge. What I know has some
importance for learning
↠ Relevance of observation. What I observe has some
importance for learning
17. corrado.mencar@uniba.it
Structural learning
1. Given an observed object o and a filter f, a
matching degree d is calculated
2. If d > threshold, then f is updated
a. Application of minimum specificity and learning principles
3. Else a new filter is added in parallel to f
a. The new filter is a sequence of description based filters corresponding
to metadata of o.
22. corrado.mencar@uniba.it
Future research
↠ Theory
→ Refinement of learning principles and structural learning
→ Extended representation of user models
→ Experiments with real-world data
↠ Application
→ Integration within the Openness platform
→ Service-oriented software system