CS3200: Adaptive Hypertext Systems - PowerPoint PPT Presentation

Title: CS3200: Adaptive Hypertext Systems


1
CS3200Adaptive Hypertext Systems
Topic 5 User Modelling

• Dr. Christopher Staff
• Department of Computer Science AI
• University of Malta

2
Aims and Objectives

• Background to user modelling
• User model implementations
• Types of user model
• Undertanding user behaviour

3
Part I Background
4
Aims and Objectives

• 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

5
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!

6
Uses of user models

• Plan recognition
• Anticipating behaviour/user actions
• User interests
• Information filtering
• User ability

7
Why a user model is required in AHS

• A user model is required to adapt hyperspace to
  reflect the users preferences, needs and
  requirements
• The level of adaptation in hypertext systems is
  summarised in the following diagram

8
(No Transcript)
9
Classifications of User Model

• Two main classifications of user model
• Analytical Cognitive
• Empirical 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

10
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

11
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

12
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/hy
  per/cyb13.htm
• Book reference http//www.ickn.org/elements/hyper
  /hyper.htm

13
1st Dimension Canonical vs. Individual

• Canonical User Model
• User model caters for one single, typical user
• Individual User Model
• Model tailors its behaviour to many different
  users

14
2nd Explicit Implicit

• Explicit User Model
• User create model himself/herself
• E.g., selecting preferences in a Web portal
• Implicit User Model
• UM built automatically by observing user
  behaviour
• Makes assumptions about the user

15
3rd Long-term vs. short-term

• Long-term user models
• Capture and manipulate long term user interests
• Can be many and varied
• Frequently difficult to determine to which
  interest the current interest belongs
• Info changes slowly over time

16
3rd Long-term vs. short-term

• Short-term user models
• Attempts to build user model within single
  session
• Very small amount of time available
• Not necessarily well defined user need
• user might not be familiar with terminology
• Short-term interest can become long term interest

17
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

18
History of User Modelling

• For instance, UM ratings stereotype/probabilis
  tic 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

19
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))

20
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
21
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)

22
History of User Modelling

• GUMS
• Adaptive system developers can define stereotype
  hierarchies
• Prolog facts describe stereotype membership
  requirements
• Rules for reasoning about them

23
History of User Modelling

• At runtime
• GUMS collects new facts about users using the
  application system
• Verifies consistency
• Informs application of inconsistencies
• Answers application queries about assumptions
  about the user

24
History of User Modelling

• Kobsa, 1990, coins User Modeling Shell System
• UMT (Brajnik Tasso, 1994)
• Truth maintenance system
• Uses stereotypes
• Can retract assumptions made about users

25
History of User Modelling

• BGP-MS (Kobsa Pohl, 1995)
• Beliefs, Goals, and Plans - Maintenance System
• Stereotypes, but stored and managed using
  first-order predicate logic and terminological
  logic
• Can be used as multi-user, multi-application
  network server

26
History of User Modelling

• Doppelgänger (Orwant, 1995)
• Info about user provided via multi-modal user
  interface
• User model that can be inspected and edited by
  user

27
History of User Modelling

• TAGUS (Paiva Self, 1995)
• Also has diagnostic subsystem and library of
  misconceptions
• Predicts user behaviour and self-diagnoses
  unexpected behaviour
• um (Kay, 1995)
• Uses attribute-value pairs to represent user
• Stores evidence for its assumptions

28
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.

29
Part II UM Implementations
30
What might we store in a UM?

• Personal characteristics
• General interests and preferences
• Proficiencies
• Non-cognitive abilities
• Current goals and plans
• Specific beliefs and knowledge
• Behavioural regularities
• Psychological states
• Context of the interaction
• Interaction history

PontusJ.pdf, ijcai01-tutorial-jameson.pdf
31
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
32
Techniques for constructing UMs

• Attribute-Value Pairs
• Machine learning techniques Bayesian
  (probabilistic)
• Logic-based (e.g.inference techniques or
  algorithms)
• Stereotype-based
• Inference rules

kules.pdf
33
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

34
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

35
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)

36
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)

37
Attribute-Value Pairs

• What do values represent?
• Degrees of interest, knowledge, familiarity, ...
• Skill level, proficiency, competence
• Facts (usually as strings, rather than numerical
  values)
• Truth or falsehood (boolean)

38
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 modeling
• Instead of working with predetermined sets of
  models, learn interests of current user

ProbUserModel.pdf
39
Simple Bayesian Classifier

• Lets 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

40
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

41
Syskill Webert

• Learns simple Baysian classifier from user
  interaction
• User identifies his/her topic of interest
• As user browses, rates web pages as hot or
  cold
• S W learns users interests to mark up links,
  and to construct search engine query

webb-umuai-2001.pdf, ProbUserModel.pdf
42
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 pages
• based on the expected ability to classify
  document if the word is absent from doc

43
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 boolean

44
Simple Bayesian Classifier

• Needs to be trained, usually using small data
  sets
• Works by multiplying probability estimates to
  obtain joint probabilities
• If any is zero, results will be zero...
• Can use small constant e (0.001) instead
  (estimation bias) ...

45
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
46
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

47
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

48
Logic-based

• Does a UM only contain facts about a users
  knowledge?
• Can we also represent assumptions, and
  assumptions about beliefs?
• Assumptions are contextualised, and represented
  using modal logic (ATac, or assumption
  typeassumption content)

pohl1999-logic-based.pdf
49
Logic-based

• We can also partition assumptions about the user

50
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

51
Stereotype-based

• Originally proposed by Rich in 1979
• Captures default information about groups of
  users
• Tends not to be used anymore

1993-aui-kobsa.pdf
52
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 stereotypes
• Fine-grained vs. coarse-grained

53
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.p
  df)

54
Adaptive Hypertext Systems

• By 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.cm
  u.edu/plb/UMUAI.ps

55
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/s
vendah/ahs.html (iui.pdf)
56
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

57
Part III Types of UM
58
Types of User Models

• User Models have their roots in philosophy and
  learning
• Student models 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

59
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/experts knowledge must be well
  understood
• Assumption that user wants to acquire experts
  knowledge
• Plan means moving from users current state to
  state that user wants to achieve

60
Student Models

• If we assume that experts knowledge is
  transferable to student, then students knowledge
  includes some of the experts knowledge
• Overlay, differential, perturbation models (from
  neena_albi_honours.pdf p25-)

61
Overlay Models

• SCHOLAR (Carbonell, 1970)
• Simplest of the student models
• Student knowledge (K) is a subset of experts
• Assumes that K missing from student model is not
  known by the student
• But what if student has incorrectly learnt K?

62
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

63
Differential Models

• WEST (Burton Brown, 1989)
• Compares student/expert performance in execution
  of current task
• Divides K into K the student should know (because
  it has already been presented) and K the student
  cannot be expected to know (yet)

64
Differential Models

• Still assumes that students K is subset of
  experts
• But can differentiate between K that has been
  presented but not understood and K that has not
  yet been presented

65
Perturbation Models

• LMS (Sleeman Smith, 1981)
• Combines overlay model with representation of
  faulty knowledge
• Bug library
• Attempts to understand why student failed to
  complete task correctly
• Permits student model to contain K not present in
  experts K

66
Part IV Understanding user behaviour
67
Making assumptions about users

• Browsing behaviour
• What does a users browsing behaviour tell us
  about the user?

68
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)

69
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
70
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
71
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
72
User Actions in Hypertext

• Actions that can be performed in hypertext
• Follow link
• Dont follow link
• Print
• Bookmark
• Go to bookmark
• Backup
• Go to URL
• ...

73
Understanding Browsing Behaviour

• What might each of these actions mean?
• Can we relate them to Kobsas assumptions?
• Do we need link analysis first?

74
Identifying Browsing Behaviour

• Lost in Hyperspace (otter2000.pdf)
• Honing in on information
• Needing more help/information
• Being un/familiar with topic/web space
• Interested in topic
• Uninterested in topic
• Changing topic

75
Identifying Browsing Behaviour

• Search browsing
• General Purpose Browsing
• The serendipitous user

catledge95.pdf
76
Understanding Browsing Behaviour

• How can understanding browsing behaviour help us
  create better adaptive hypertext systems?
• Less intrusive
• Just-in-Time support
• Dont give more info when it is not
  required/wanted
• Efficient use of resources

77
Conclusions

• The ability to model the user allows reasoning
  about the user to tailor an interaction to the
  users needs and requirements...
• ... especially when the user is unable to
  describe what it is they need
• Tightly bound to domain/expert knowledge

78
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