csa3212: topic 5 © 2005- chris staff 1 of 78 [email protected] university of malta csa3212:...

78
CSA3212: Topic 5 © 2005- Chris 1 of 78 [email protected] University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department of Intelligent Computer Systems University of Malta Topic 5: User Modelling

Upload: gary-warren

Post on 18-Jan-2016

222 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

CSA3212: Topic 5© 2005- Chris Staff

1 of [email protected] University of Malta

CSA3212:User-Adaptive Systems

Dr. Christopher StaffDepartment of Intelligent Computer Systems

University of Malta

Topic 5: User Modelling

Page 2: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

2 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Aims and Objectives

Background to user modellingUser model implementationsTypes of user modelUnderstanding user behaviour

Page 3: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

CSA3212: Topic 5© 2005- Chris Staff

3 of [email protected] University of Malta

Part I: Background

Page 4: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

4 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Aims and Objectives

User-adaptive systems in general need to represent the user in some way so that the system (interface and/or data) can be adapted to reflect the user's interests, needs and requirements

The representation of the user is called a user profile or a user model

Page 5: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

5 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Aims and Objectives

UM has its roots in philosophy/AI, and the first implementations were in the field of natural-language dialogue systems

For adaptive systems, user model must learn (at least some of the) user requirements/preferences

User models can be simple or complex, but remember that you can only get out of them what you put in!

Page 6: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

6 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Uses of user models

Plan recognitionAnticipating behaviour/user actionsUser interestsInformation filteringUser ability…

Page 7: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

7 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Why a user model is required in UAS

A user model is required to adapt the information space to reflect the users preferences, needs and requirements, amongst others

The level of adaptation in adaptive hypermedia systems is summarised in the following diagram, but can also apply to UASes

Page 8: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

8 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Page 9: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

9 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Classifications of User Model

Two main classifications of user modelAnalytical CognitiveEmpirical Quantitative

Reference: G. Brajnik, G. Guida and C. Tasso, “User Modelling in Intelligent

Information Retrieval” in Information Processing and Management, Vol. 23, 1987, pp. 305-320

Page 10: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

10 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Empirical Quantitative Empirical quantitative models make no effort to

understand or reason about the user Contain surface knowledge about the user Knowledge about the user is taken into

consideration explicitly only during the design of the system and is then hardwired into the system (early expert systems)

E.g., models for novice, intermediate, expert users Fit the current user into one of the stored models

Page 11: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

11 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Analytical Cognitive Try to simulate the cognitive user processes that

are taking place during permanent interaction with the system

These models incorporate an explicit representation of the user knowledge

The integration of a knowledge base that stores user modelling information allows for the consideration of specific traits of various users

Page 12: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

12 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Taxonomies of User Models

Rich classifies analytical user models along three dimensions Rich, E.A. (1983): 'Users are Individuals : Individualising User Models',

in International Journal of Man-Machine Studies, Volume 18. (http://www.cs.utexas.edu/users/ear/IJMMS.pdf)

Gloor, P. (1997), Elements of Hypermedia Degisn, Part I (Structuring Information) Chapter 2 (user Modeling) Section 1 (Classifications and Taxonomy).

Section reference: http://www.ickn.org/elements/hyper/cyb13.htm Book reference: http://www.ickn.org/elements/hyper/hyper.htm

Page 13: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

13 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

1st Dimension: Canonical vs. Individual

Canonical User ModelUser model caters for one single, typical user

Individual User ModelModel tailors its behaviour to many different

users

Page 14: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

14 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

2nd: Explicit & Implicit

Explicit User ModelUser creates model himself/herselfE.g., selecting preferences in a Web portal

Implicit User ModelUM built automatically by observing user

behaviourMakes assumptions about the user

Page 15: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

15 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

3rd: Long-term vs. short-term

Long-term user modelsCapture and manipulate long term user interestsCan be many and variedFrequently difficult to determine to which

interest the current interest belongsInfo changes slowly over time

Page 16: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

16 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

3rd: Long-term vs. short-term

Short-term user modelsAttempts to build user model within single

sessionVery small amount of time availableNot necessarily well defined user need

user might not be familiar with terminology

Short-term interest can become long term interest…

Page 17: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

17 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

History of User Modelling

UM and its history are linked to the history of user-adaptive systems

Based on the way in which the UM updates its model of the user, the domain in which it is used, and the way the interface is caused to change

Page 18: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

18 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

History of User Modelling

For instance, UM + ratings = stereotype/probabilistic recommender system

UM + hypertext + adaptation rules = AHS UM + user goals + pedagogy + adaptation rules =

ITS UM representation, and how it learns about its

users tends to depend on the domain

Page 19: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

19 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

History of User Modelling Focusing on generic user modelling Has its roots in dialogue systems and philosophy

Need to model the participants to disambiguate referents, model the participants’ beliefs, etc.

Early systems (pre-mid-1985) had user modelling functionality embedded within other system functionality (e.g., Rich (recommendation system); Allen, Cohen & Perrault (dialogue processing))

Page 20: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

20 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

History of User Modelling

From 1985, user modelling functionality was performed in a separate module, but not to provide user modelling services to arbitrary systems

So one branch of user modelling focuses on user modelling shell systems

2001-UMUAI-kobsa (UM history).pdf

Page 21: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

21 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

History of User Modelling

Although UM has its roots in dialogue systems and philosophy, more progress has been made in non-natural language systems and interfaces (PontusJ.pdf)

GUMS (General User Modeling System) first to separate UM functionality from application - 1986 (Finin)

Page 22: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

22 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

History of User Modelling

GUMSAdaptive system developers can define

stereotype hierarchiesProlog facts describe stereotype membership

requirementsRules for reasoning about them

Page 23: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

23 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

History of User Modelling

At runtime:GUMS collects new facts about users using the

application systemVerifies consistencyInforms application of inconsistenciesAnswers application queries about assumptions

about the user

Page 24: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

24 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

History of User Modelling

Kobsa, 1990, coins “User Modeling Shell System”

UMT (Brajnik & Tasso, 1994): Truth maintenance systemUses stereotypesCan retract assumptions made about users

Page 25: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

25 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

History of User Modelling

BGP-MS (Kobsa & Pohl, 1995)Beliefs, Goals, and Plans - Maintenance SystemStereotypes, but stored and managed using

first-order predicate logic and terminological logic

Can be used as multi-user, multi-application network server

Page 26: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

26 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

History of User Modelling

Doppelgänger (Orwant, 1995)Info about user provided via multi-modal user

interfaceUser model that can be inspected and edited by

user

Page 27: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

27 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

History of User Modelling

TAGUS (Paiva & Self, 1995)Also has diagnostic subsystem and library of

misconceptionsPredicts user behaviour and self-diagnoses

unexpected behaviour

um (Kay, 1995)Uses attribute-value pairs to represent userStores evidence for its assumptions

Page 28: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

28 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

History of User Modelling

From 1998 and with the popularisation of the Web, web personalisation grew in the areas of targeted advertising, product recommendations, personalised news, portals, adaptive hypertext systems, etc.

Page 29: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

CSA3212: Topic 5© 2005- Chris Staff

29 of [email protected] University of Malta

Part II: UM Implementations

Page 30: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

30 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

What might we store in a UM?

Personal characteristicsGeneral interests and preferencesProficienciesNon-cognitive abilitiesCurrent goals and plansSpecific beliefs and knowledgeBehavioural regularitiesPsychological statesContext of the interactionInteraction history

PontusJ.pdf, ijcai01-tutorial-jameson.pdf

Page 31: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

31 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

From where might we get input? Self-reports on personal characteristics Self-reports on proficiencies and interests Evaluations of specific objects Responses to test items Naturally occurring actions Low-level measures of psychological states Low-level measures of context Vision and gaze tracking

ijcai01-tutorial-jameson.pdf

Page 32: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

32 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Techniques for constructing UMs

Attribute-Value PairsMachine learning techniques & Bayesian

(probabilistic)Logic-based (e.g.inference techniques or

algorithms) Stereotype-based Inference rules

kules.pdf

Page 33: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

33 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Attribute-Value Pairs

e.g., ah2002AHA.pdf The representation of the user and of the domain

are inextricably linked What we want to do is capture the “degree” to

which a user “knows” or is “interested” in some concept

We can then use simple or complex rules to update the UM and to adapt the interface

Page 34: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

34 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Attribute-Value Pairs

Particularly useful for showing (simple) dependencies between concepts Complex ones harder to update

Can use IF-THEN-ELSE rules to trigger events Such as updating a user model Modifying the contents of a document (AHA!,

MetaDoc) Changing the visibility or viability of links

Page 35: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

35 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Overview of AHA! Adaptive Hypertext for All! Each time user visits a page, a set of rules

determines how the user model is updated Inclusion rules determine the fragments in the

current page that will be displayed to the user (adaptive presentation)

Requirement rules change link colours to indicate the desirability of each link (adaptive navigation)

Page 36: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

36 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Attribute-Value Pairs

From where do the attributes come?Need to be meaningful in the domain

(domain modelling)Can be concepts (conceptual modelling)Can be terms that occur in documents

(IR)

Page 37: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

37 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Attribute-Value Pairs

What do values represent?Degrees of interest, knowledge,

familiarity, ...Skill level, proficiency, competenceFacts (usually as strings, rather than

numerical values)Truth or falsehood (boolean)

Page 38: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

38 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Simple Bayesian Classifier

Rather than pre-determining which concepts, etc., to model, let features be selected based on observation

SBCs are also used in machine learning approaches to user modelingInstead of working with predetermined sets of

models, learn interests of current user

ProbUserModel.pdf

Page 39: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

39 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Simple Bayesian Classifier Let’s say we want to determine if a document is

likely to be interesting to a user We need some prior examples of interesting and

non-interesting documents Automatically select document features

Usually terms of high frequency Assign boolean values to terms in vectors

To indicate presence in or absence from document

Page 40: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

40 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Simple Bayesian Classifier

Now, for an arbitrary document, we want to determine the probability that the document is interesting to the user

P(classj | word1 & word2 & ... wordk)Assuming term independence, the

probability that an example belongs to classj is proportional to

P(class j ) P (wordi | class j )i

k

Page 41: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

41 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Syskill & Webert

Learns simple Bayesian classifier from user interaction

User identifies his/her topic of interestAs user browses, rates web pages as “hot”

or “cold”S & W learns user’s interests to mark up

links, and to construct search engine query

webb-umuai-2001.pdf, ProbUserModel.pdf

Page 42: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

42 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Syskill & Webert

Text is converted to feature vectors (term vectors) for SBC

Terms used are those identified as being “most informative” words in current set of pagesbased on the expected ability to classify

document if the word is absent from doc

Page 43: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

43 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Simple Bayesian Classifier

Of course, the term independence assumption is unrealistic, but SBC still works well

Algorithm is fast, so can be used to update user model in real time

Can be modified to support ranking according to degree of probability, rather than binary

Page 44: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

44 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Simple Bayesian Classifier

Needs to be “trained”, usually using small data sets

Works by multiplying probability estimates to obtain joint probabilitiesIf any is zero, results will be zero...Can use small constant (0.001) instead

(estimation bias) ...

Page 45: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

45 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Personal WebWatcher

Predicting interesting hyperlinks from the set of documents visited by a user

Followed links are positive examples of user interests

Ignored links are negative examples of user interests

Use descriptions of hyperlinks as “shortened documents” rather than full docs

pwwTR.pdf

Page 46: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

46 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Personal WebWatcher

Also uses a simple Bayesian classifier to recommend interesting links

where

TF(w, c) is term frequency of term w in document of class c (e.g., interesting/non-interesting), and TF(w, doc) is frequency of term w in document doc

P(c | doc) P(c)

w P (w |c)TF ( w,doc )

P (c i )w

P(w |c i )TF( w ,doc )

p(w |c) 1 TF (w,c)

# words TF (w i,c)i

Page 47: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

47 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Personal WebWatcher

“Training” set is set of documents that user has seen and user could have seen but has ignored

Uses short description of document, rather than document vector itself

Page 48: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

48 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Logic-based

Does a UM only contain facts about a user’s knowledge?

Can we also represent assumptions, and assumptions about beliefs?

Assumptions are contextualised, and represented using modal logic (AT:ac, or assumption type:assumption content)

pohl1999-logic-based.pdf

Page 49: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

49 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Logic-based

We can also partition assumptions about the user

Page 50: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

50 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Logic-based

Advantage is that beliefs, assumptions, facts are already in logical representation

Makes it easier to draw conclusions about the user from the stored knowledge

Page 51: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

51 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Stereotype-based

Originally proposed by Rich in 1979Captures default information about groups

of usersTends not to be used anymore

1993-aui-kobsa.pdf

Page 52: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

52 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Stereotype-based

Kobsa points out that developer of stereotypes needs to fulfil three tasks Identify user subgroups Identify key characteristics of typical user in subgroup

So that new user may be automatically classified

Represent hierarchically ordered stereotypesFine-grained vs. coarse-grained

Page 53: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

53 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Inference rules e.g., C-Tutor, avanti.pdf May use production rules to make inferences

about user Also, to update system about changes in user state

or user knowledge Note that Pohl points out that all user models (that

learn about the user) must infer assumptions about the user (pohl1999-logic-based.pdf)

Page 54: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

54 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Adaptive Hypertext Systems

“[B]y adaptive hypermedia we mean all hypertext and hypermedia systems which

reflect some features of the user in the user model and apply this model to adapt various

visible aspects of the system to the user”Brusilovsky, P. (1996). Methods and techniques of adaptive hypermedia, in User Modeling

and User-Adapted Interaction 6 (2-3), pp. 87-129. Available on-line at: http://www.contrib.andrew.cmu.edu/~plb/UMUAI.ps

Page 55: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

55 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Adapted from Horgen, S.A., 2002, "A Domain Model for an Adaptive Hypertext System based on HTML", MSc Thesis, Chapter 4 (Adaptivity), pg. 32. Available on-line from http://www.aitel.hist.no/~svendah/ahs.html (iui.pdf)

Page 56: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

56 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Conclusion

User Models can represent user beliefs, preferences, interests, proficiencies, attitudes, goals

User models are used in AHS to modify hyperspace In IR to select better (more relevant) documents

More likely to use analytical cognitive model, but can still use “simple” models

Page 57: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

CSA3212: Topic 5© 2005- Chris Staff

57 of [email protected] University of Malta

Part III: Types of UM

Page 58: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

58 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Types of User Models

User Models have their roots in philosophy and learning

Student model assumed to be some subset of the knowledge about the domain to be learnt

Consequently, the types of user model have been heavily influenced by this

Page 59: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

59 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Student Models Student Models are used, e.g., in Intelligent

Tutoring Systems (ITSs) In ITS we know user goals, and may be able to

identify user plans The domain/expert’s knowledge must be well

understood Assumption that user wants to acquire expert’s

knowledge Plan means moving from user’s current state to

state that user wants to achieve

Page 60: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

60 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Student ModelsIf we assume that expert’s knowledge is

transferable to student, then student’s knowledge includes some of the expert’s knowledge

Overlay, differential, perturbation models (from neena_albi_honours.pdf p25-)

Page 61: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

61 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Overlay Models

SCHOLAR (Carbonell, 1970)Simplest of the student modelsStudent knowledge (K) is a subset of

expert’sAssumes that K missing from student model

is not known by the studentBut what if student has incorrectly learnt K?

Page 62: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

62 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Overlay Models

Good when subject matter can be represented as prerequisite hierarchy

K remaining to be acquired by student is exactly difference between expert K and student K

Cannot represent/infer student misconceptions

Page 63: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

63 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Differential Models

WEST (Burton & Brown, 1989)Compares student/expert performance in

execution of current taskDivides K into K the student should know

(because it has already been presented) and K the student cannot be expected to know (yet)

Page 64: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

64 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Differential Models

Still assumes that student’s K is subset of expert’s

But can differentiate between K that has been presented but not understood and K that has not yet been presented

Page 65: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

65 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Perturbation Models

LMS (Sleeman & Smith, 1981)Combines overlay model with

representation of faulty knowledgeBug library

Attempts to understand why student failed to complete task correctly

Permits student model to contain K not present in expert’s K

Page 66: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

CSA3212: Topic 5© 2005- Chris Staff

66 of [email protected] University of Malta

Part IV: Understanding user behaviour

Page 67: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

67 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Making assumptions about users

Browsing behaviourWhat does a user’s browsing behaviour tell us

about the user?

Page 68: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

68 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Making assumptions about users

Searle (1969)... when a speech act is performed certain presuppositions must have been valid for the speaker to perform the speech act correctly (from 1995-UMUAI-kobsa.pdf, 1995-COOP95-kobsa.pdf)

Page 69: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

69 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Making assumptions about users

If the user requests an explanation, a graphic, an example or a glossary definition for a hotword, then he is assumed to be unfamiliar with this hotword.

1996-kobsa.pdf

Page 70: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

70 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Making assumptions about users

If the user unselects an explanation, a graphic, an example or a glossary definition for a hotword, then he is assumed to be familiar with this hotword.

1996-kobsa.pdf

Page 71: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

71 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Making assumptions about users

If the user requests additional details for a hotword, then he is assumed to be familiar with this hotword.

1996-kobsa.pdf

Page 72: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

72 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

User Actions in Hypertext Actions that can be performed in hypertext

Follow link Don’t follow link Print Bookmark Go to bookmark Backup Go to URL ...

Page 73: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

73 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Understanding Browsing Behaviour

What might each of these actions mean?Can we relate them to Kobsa’s

assumptions?Do we need link analysis first?

Page 74: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

74 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Identifying Browsing Behaviour

Lost in Hyperspace (otter2000.pdf)Honing in on informationNeeding more help/informationBeing un/familiar with topic/web spaceInterested in topicUninterested in topicChanging topic

Page 75: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

75 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Identifying Browsing Behaviour

Search browsing“directed search; where the goal is known”

General Purpose Browsing“consulting sources that have a high likelihood

of items of interest”

The serendipitous user“purely random”

catledge95.pdf

Page 76: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

76 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Understanding Browsing Behaviour

How can understanding browsing behaviour help us create better adaptive hypertext systems?Less intrusiveJust-in-Time supportDon’t give more info when it is not

required/wantedEfficient use of resources

Page 77: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

77 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Conclusions

The ability to model the user allows reasoning about the user to tailor an interaction to the user’s needs and requirements...

... especially when the user is unable to describe what it is they need

Tightly bound to domain/expert knowledge

Page 78: CSA3212: Topic 5 © 2005- Chris Staff 1 of 78 chris.staff@um.edu.mt University of Malta CSA3212: User-Adaptive Systems Dr. Christopher Staff Department

78 of [email protected] University of Malta

CSA3212: Topic 5© 2005- Chris Staff University of Malta

Conclusions

Significant efforts to decouple the user model from the application

May be too expensive to accurately model all domains, and in any case, goal of many adaptive systems is not to help user become expert, but to provide timely assistance at the right level of detail