Adaptive interactive systems
(INFOMAIS)
2023/2024
,Lecture 1. Introduction
This course is about the design and evaluation of interactive systems that automatically adapt to
users and their context.
Adaptive systems
• Every child knows an adaptive system
• And systems are not always perfect
• And some systems are more complex
• On the web, we encounter adaptive systems on a daily basis.
Motivation – Why adaptation?
• In the plethora of information, we have to find the right, relevant item
• Seminal example of choice overload (more products: 3% sale, less products: 30% sale)
• Information and choice overload – two irrelated problems
o Originates in information theory
o Exposure to or provision of too much information (or data)
o Humans have fairly limited cognitive processing capacity thus
• With information overload, it is likely that decision quality decreases
• We need to filter information
• Information curation (also called content curation)
o Carried out (manually) by specially designated curators e.g.
▪ Museums and galleries have curators to select items for collection and display
▪ Music labels select artists (and songs) that are recorder and marketed
▪ DJs of radio stations select songs to be played on air
▪ Journalists research, filter, and select the information that is communicated to
the public
There are multiple stakeholders involved
Addressing consumers is economically important – but its effectiveness is suffering
• It is increasingly difficult to attract consumers’ attention (Pieters et al. 2002)
• Consumers are overwhelmed by the quantity of advertising messages (Ha and McCann
2008)
• Consumers suffer from information overload in general
Digital signage: Information overload does not only happen on the Web but also in physical space.
,Attention: A majority of consumers do not look at displays. Even less pay attention to the contents.
“We need the ‘right’ information, at the ‘right’ time, in the ‘right’ place, in the ‘right’ way, to the
‘right’ person.”
Users
• One size does not fit all.
• Everyone is different and has different preferences and demands.
Personalization: tailoring a service or a product to meet someone’s individual requirements
-> leads to higher relevance
• Segmentation
▪ discovering and addressing groups of individuals with a common, yet broad, set of
characteristics
▪ e.g., geographic location, interests, time of visit, etc.
• Personalization
▪ it is segmentation stripped to its roots—the individual
▪ tailoring at the most personal individual level
Terms are not always used as defined
• Where are the boundaries between segmentation and personalization?—It tends to be
blurry.
• Recommendations are often referred to as being “personalized in any case”, which is not
necessarily true. e.g.,
o Recommendations solely based on gender or country of residence
o Recommendations of what is currently popular or trendy on a platform
• Is so-called “targeted advertising” a personalization or a segmentation approach? It depends.
➔ It is not all about the person—(also) the situation matters.
o It depends on the person
o It depends on the situation
o An ideal intelligent system is aware of its context —both the person as well as the
situation— and adapts to it.
➔ Music may adapt in real-time to the situation (e.g., activity levels).
o e.g., potentially relevant context elements for restaurant recommendation.
Adaptive virtual voice assistants: Apple’s Siri, Google Assistant, Amazon’s Alexa etc.
, Lecture 2. User Modelling
Why User Models?: Every user is different, has different needs, preferences
Terminology -> User: U, Item: I, System: S, Time: T
What is a user model?
• A user model is an internal representation of user characteristics used by a system (as a basis
for adaption).
• A user model is a specification of user characteristics aiming to facilitate reasoning about
the user’s needs, preferences, and behavior.
List of frequent User Characteristics
• Age, gender, location, level of education, job title…
• Knowledge, experience, expertise, competence…
• Personality, cognitive/learning style…
• Interests, preferences, habits, ...
• Needs, goals, tasks, …
• Mental states,...
• Emotional state, mood, tired, stressed, ...
• Cultural background, ....
• Interaction patterns, ..
Which characteristics are really relevant?: Depends on the system’s goals, time frame, available
data, and the required accuracy.
User modeling: User Modeling is the process of creating and updating a user model, by deriving user
characteristics from user data —which is data that is explicitly provided by the user or data that
stems from indirect events and observations.
Explicit and Implicit User Modelling
Explicitly provided/stated characteristics by the users themselves (explicit information)
➔ Representations of these characteristics
Characteristics inferred form the (raw) user data of U (implicit information)
➔ Estimates from the system S
User modeling process
1. Acquisition of user data
2. Inference of knowledge from the data
3. Representation of the user model
4. Updating a user mode
1. Acquisition of user data
1. System ask questions -> User answer -> User model is constructed -> System output is
adapted to user model
Or
