1 of 52

1
CSA4080Adaptive Hypertext Systems II
Topic 5 Recommendation Techniques

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

2
Aims and Objectives

• Global Reconnaissance Techniques
• PowerScout
• Watson
• HyperContext
• Recommender Systems
• Amazon
• IMDB

3
Aims and Objectives

• User Modelling in IR
• User Modelling in Recommender Systems

4
Readings

• recommender p36-soboroff.pdf
• SOTA Recommender systems Lit Review.pdf (Chapter
  8 - )
• recommender 0329_050103.pdf

5
What is Recommendation?

• Recommendations are suggestions
• It could be a suggestion to watch a particular
  movie, or to buy a particular product, visit a
  restaurant (not fish!)
• In hyperspace, this could be a suggestion to
  follow a path leading to a relevant document, or
  to visit a document directly

6
What is Recommendation?

• If the recommendation is to do with guidance,
  then this is related to adaptive navigation
• If the recommendation is based mainly on
  recommending products, then it is a recommender
  system
• The two are, or can be, closely related, but the
  literature tends to deal with them separately

7
Examples...

• Global Reconnaissance, Guidance, Personal
  Information Management Assistants...
• As you browse a user model of your interests is
  automatically built
• Paths are recommended, or other documents are
  collected for your perusal
• Usually use IR systems to index, search for, and
  retrieve relevant documents

8
Global Reconnaissance

• PowerScout (Lieberman, 2001)
• Automatically builds user model from recently
  viewed pages, but based on users long-term
  interaction
• Searches for relevant documents via 3rd party
  search engine
• Organises results by Concept

Why-Surf-Alone.pdf
9
Global Reconnaissance

• Watson (Budzik et al, 1998)
• Observes user interacting with several
  application to build model of users information
  goal
• Anticipates that user is interested in documents
  similar to ones seen in recent past
• Searches for documents (via 3rd party search
  engine) and presents list to user
• Short-term user model, with long-term support

budzik99watson.pdf
10
Global Reconnaissance

• HyperContext (Staff, 2000)
• Uses Adaptive Information Discovery (AID)
  techniques to find remote but relevant
  information
• Short-term UM, with long-term UM support

HCTCh5.pdf
11
More examples...

• Recommender systems
• Content recommendation
• Collaborative recommendation

12
Recommender Systems

• What did you think about...? Did you like...?
• Make recommendation based on past experience
• Real world examples food critic, movie critic,
  book/novel critic, lecture course critic -)

13
Recommender Systems

• How do you know you can trust somebodys
  recommendation?
• Because experience has taught you?
• Because critic is trusted source of info?
• Because a friend/expert likes movies/novels/ food
  you like?
• ???

14
Recommender Systems

• Generally two types of recommender system
• Content-based recommendation
• Collaborative recommendation
• burke-umuai02.pdf
• recommender 0329_050103.pdf

15
Recommender SystemsCollaborative Recommendation

• Usually, ratings-based feedback
• Users must indicate degree to which they like
  product, product is fit for purpose, etc
• The recommendation is based on the weighted
  average utility of the product...
• ... of users with the same preferences!
• preferences may also include demographics

16
Recommender SystemsCollaborative Recommendation

• Do you want recommendations based on all users?
• Or do you want recommendations from other people
  like you, with your tastes and preferences?
• How can the system work out what you
  like/prefer/want?
• Comparing interactions (purchases, queries,
  movies seen, etc.) and identifying trends

17
Recommender SystemsCold-Start Problem

• Collaborative recommender systems suffer from the
  cold start problem
• How do you recommend a new product with no
  ratings?
• How do you recommend to a new user?
• Content-based recommendation overcomes some
  problems

18
Recommender SystemsContent-based

• Instead of using ratings, use product features
• Identify features using eg., kdd96_quest.pdf
• On what basis can products be compared? Genre,
  cost, dimensions, etc.
• Recommendations can be based on user-selected
  feature sets, or on prior interactions
• Latter works for frequent recommendations of
  similar product (e.g., movie) but not infrequent
  ones, e.g., camera purchase

19
Recommender SystemsCold-Start Problem Revisited

• If user categorisation is automatic (i.e., System
  believes user U belongs to group G based on past
  interactions) then cold-start problem for new
  users
• New products are ok, though, because they will be
  recommended based on feature similarity
• If user drives feature selection, then is system
  user-adaptive?

20
Recommender Systems

• Both collaborative and content-based
  recommendation utilise clustering techniques to
  identify patterns in users and/or products/items
• Most common technique is the Vector Space Model
  (Topic 6)
• Other IR techniques also used

21
User Modelling in IR andRecommender Systems

• User model is usually created and maintained for
  information retrieval and recommender systems

22
User Modelling

• In pure IR, user interaction is usually geared
  towards selecting relevant documents from a
  collection/repository

23
User Modelling

• Is there a user model, even a simple one, in this
  model of IR?
• If there is, is there a point at which adaptation
  might be said to take place?
• More next topic...

24
User Modelling in IR

• This part based heavily on www.scils.rutgers.edu/
  belkin/um97oh/

25
User Modelling in IR

• In early IR (before automation!) human mediators
  (e.g., librarians) construct queries on behalf of
  users
• See also, evaluation of boolean model
  (p289-blair.pdf)
• Search intermediaries still used in some
  Web-based question-answering systems, e.g.,
  AskJeeves

26
User Modelling in IR

• As query specification languages became complex
  (1950s/60s) intermediaries needed to construct
  queries
• It became useful in systems like SDI to store
  representations of users long-term interests so
  that new information objects could be routed to
  them

27
User Modelling in IR

• Initially, user profiles were changed manually on
  basis of users evaluation of search results
• Eventually, SDI could automatically modify
  profiles based on relevance judgements
• This line of IR developed into information
  filtering (routing)

28
User Modelling in IR

• Ad hoc IR assumes that information need is just
  one-time
• there is just one information seeking episode
• a single query is compared to a static document
  collection
• If there is a subsequent query that is submitted
  by the same user and that is related to a prior
  query, it is treated as a new episode

29
User Modelling in IR

• In ad hoc IR user may need support to
• Reformulate the query to get better results
• Provide relevance feedback so that system can
  modify the query (Rocchio, 1966)
• In queryless IR (Oddy, 1977) the user need not
  specify the information need
• user evaluates/rates features of retrieved info
• system builds model of users interests

30
User Modelling in IR

• ASK-based IR (Belkin et al, 1982)
• elicits and represents users Anomalous State of
  Knowledge rather than specific info need
• Associative network represents ASK
• Uses rules to compare ASK with document
  representations
• User ratings of features can auto update ASK

31
User Modelling in IR

• Modelling user goals (Vickery, Vickery Brooks,
  1980s)
• to determine the comparison techniques to apply
  for different users
• users direct elicitation implication from user
  behaviour
• long term modelling of user preferences and
  typical info problems

32
User Modelling in IR

• Models for identifying UM functions in IR
• Abstract analysis of IR task. To identify
• goals of IR
• problems in achieving goals
• whats necessary for other actors in the system
  to know of user to achieve goals/overcome
  problems
• query as specification as modelling function

33
User Modelling in IR

• IR interaction as dialogue
• what is needed to experience effective
  conversation (e.g., Grices rules of
  conversational implicature)
• how can these be modelling in an IR interaction?
• models of understanding that each actor has of
  the other (I believe that you believe..., and
  see Kobsas BGP-MS)

34
User Modelling in IR

• Observing user behaviour in IR systems settings
• cognitive task analysis
• failure analysis
• thinking aloud, etc.
• Stereotypical models of experience, expertise,
  search behaviours, needs

35
User Modelling in IR

• Overall goal (not Belkins words!)
• Intelligent agents that can understand user
  needs/goals/tasks by observing user behaviour and
  that can find, retrieve, or even accomplish, what
  the user had set out to do, without the user
  necessarily expressing his or her intentions

36
User Modelling in Recommender Systems

• Recommender systems
• Content-based (very similar to IR)
• Collaborative
• Aim is to make recommendations based on what
  other, similar, users liked or did

recommender 0329_050103.pdf
37
User Modelling in RS

• In general, let C be the set of all users, and
  let S be the set of all recommendable items (CDs,
  books, movies, holidays, documents...)
• Let u be a utility function which measures the
  usefulness of item s to user c
• uC x S ? R
• where R is a totally ordered set (of, e.g.,
  reals)

38
User Modelling in RS

• In RS, utility of an item to a user is usually
  represented as a rating, how much a particular
  user liked the item, but it can be any function
• On what basis do we decide that two users are
  similar?

39
User Modelling in RS

• What information is retained about users?
• Demographic information
• Interaction history
• Ratings given to items

40
User Modelling in RS

• Two main types of algorithm
• Memory-based
• Model-based

41
User Modelling in RS

• Memory-based algorithm
• heuristics that make rating predictions based on
  entire collection of previously rated items by
  users
• Predict rating for user c on item s assuming user
  has not previously seen item (simplest)

where C is set of N users c that are most
similar to user c and who have rated item s
42
User Modelling in RS

• Problem with simplest algorithm...
• Doesnt take into account similarity between
  users, only similarity between prior ratings
• sim(c,c) is the similarity (distance measure)
  between two users, k is a normalising function

43
User Modelling in RS

• Many ways of deriving user similarity measure
• Normally based on the set of items, Sxy, that
  both users, x and y, have rated
• Two popular approaches
• Cosine-based
• Correlation-based

44
User Modelling in RS

• Correlation-based approach
• where rx is the average rating given by user x

_
45
User Modelling in RS

• Cosine-based approach
• 2 users x and y are treated as vectors in
  m-dimensional space, where m is the number of
  items in Sxy

46
User Modelling in RS

• Memory-based approaches need many ratings to work
  well
• Default voting improves rating prediction accuracy

47
User Modelling in RS

• Model-based algorithm to measure user similarity
• uses collection of ratings to learn a model which
  is then used to make rating predictions
• the probability that user c will give a
  particular rating to item s given that users
  ratings of the previously rated items (Breese et
  al, 1998).

48
User Modelling in RS

• Breese et al proposed two alternative
  probabilistic models to estimate the probability
  expression
• Cluster model (Naive baysian)
• Users are clustered into groups
• Baysian networks
• Each item is a node in the network, with states
  of each node represent possible rating values
• Network and conditional probabilities are learned
  from data

49
Collaborative System Shortcomings

• New user problem
• New item problem
• Sparsity
• Can initially be resolved using demographic data

50
Conclusion

• IR has users with both long- and short-term
  interests
• RS has users with mainly long-term interests,
  although recommendations may be made to users
  with short-term interests
• In which case, the method of interaction is
  usually different, and recommendations are based
  on content

51
Conclusion

• In IR, an explicit user model is maintained for
  long-term support, but a query is a reasonable ad
  hoc model of the users interest
• In RS, users need to be distinguished in the
  collaborative model, but not in the content model

52
Conclusion

• In the next topic we will look at IR models and
  techniques
• Vector-based model
• Probabilistic model
• Relevance Feedback
• Query Reformulation
• We will also look at knowledge and domain
  representation