research challenges in group recommender systems judith masthoff
TRANSCRIPT
![Page 1: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/1.jpg)
Research Challenges in Group Recommender
Systems
Judith Masthoff
![Page 2: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/2.jpg)
The University of Aberdeen, Scotland
• Founded 1495• 5th oldest university in the UK• 14,000 students• 120 nationalities• 550+ first degree programmes• 110+ taught postgraduate
programmes
![Page 3: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/3.jpg)
Contents
• Introduction to group recommender systems• Five challenges:
• Evaluation and metrics• Recommending sequences• Modelling satisfaction• Incorporating group attributes• Explaining group recommendations
![Page 4: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/4.jpg)
Introduction to Group Recommender
Systems
![Page 5: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/5.jpg)
Introduction
• Group Recommender Systems: how to adapt to a group of people rather than to an individual
I know individual ratings of Peter, Jane,
and Mary. What to recommend to the
group?
![Page 6: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/6.jpg)
How do groups make decisions?
• Split yourself into groups of 4-6 people• Decide what your group would listen to
if time for 1 song, for 2 songs, for 3 songs, for 4 songs
A B C D E
F G H I J K
![Page 7: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/7.jpg)
What would you recommend?
A B C D E F G H I J
Peter 10 4 3 6 10 9 6 8 10 8
Jane 1 9 8 9 7 9 6 9 3 8
Mary 10 5 2 7 9 8 5 6 7 6
![Page 8: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/8.jpg)
[Masthoff, 2004]• Plurality Voting• Average• Multiplicative• Borda count• Copeland rule• Approval voting• Least misery• Most pleasure• Average without misery• Fairness• Most respected person
Many strategies exist
• Graph-based ranking [Kim et al, 2013]
• Spearman footrule rank [Baltrunas et al, 2010]
• Nash equilibrium [Carvalho & Macedo, 2013]
• Purity [Salamó et al, 2012]• Completeness
[Salamó et al, 2012]• ……….
![Page 9: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/9.jpg)
Average Strategy
A B C D E F G H I J
Peter 10 4 3 6 10 9 6 8 10 8
Jane 1 9 8 9 7 9 6 9 3 8
Mary 10 5 2 7 9 8 5 6 7 6
Group list: (E, F), H, (D, J), A, I, B, G, C
7 6 4.3 7.3 8.7 8.7 5.7 7.7 6.7 7.3
Use average of the individual ratings
![Page 10: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/10.jpg)
Least misery strategy
A B C D E F G H I J
Peter 10 4 3 6 10 9 6 8 10 8
Jane 1 9 8 9 7 9 6 9 3 8
Mary 10 5 2 7 9 8 5 6 7 6
Group list: F, E, (H, J, D), G, B, I, C, A
1 4 2 6 7 8 5 6 3 6
Use minimum of the individual ratings
![Page 11: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/11.jpg)
Challenge 1: Evaluation and Metrics
![Page 12: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/12.jpg)
Slicing and Dicing
• Want to know why a group recommender system works / does not work
• Slicing: Layered evaluation (Paramythis et al, 2010)
– Break adaptation process down into its constituents (“layers”)
– Evaluate layers separately• Dicing
– Break system down into separate functionalities (e.g. provide recommendations, explain recommendations)
– Evaluate functionalities separately
![Page 13: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/13.jpg)
Layered evaluation
Layered Evaluation – Recap
Presence tracking
Group recommendation
Explicit ratings, user’s viewing
actions
Show top recommendations
by stars
Rank items to recommend
How much user liked viewed items
What the individuals in the group (dis)like, how
they are feeling
Most of this presentation focusses on one layer (DA or UM)
![Page 14: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/14.jpg)
• What does it mean for a group recommender strategy to be good?
• For the group to be satisfied? • But how do you measure the satisfaction of a
group?
How to evaluate how good a strategy is?
![Page 15: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/15.jpg)
Metrics (1)
• Utility for the group
This is what most researchers do, they take the average of the individuals’ ratings (or average of a comparison of rankings of items).
What is the problem with this?
![Page 16: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/16.jpg)
Metrics (2)
• Whether all individuals exceeded a minimum level of satisfaction
When? After a sequence of items? At each point in the sequence?
What is the problem with this?
![Page 17: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/17.jpg)
Metrics (3)
Extent to which group members• Think it is fair?• Think it is best for the group?• Accept the recommendation for the group?• Do not exhibit negative emotions?
With or without having seen the options and individual preferences?
What is the problem with this?
![Page 18: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/18.jpg)
Metrics (4)
Extent to which independent observers• Think it is fair?• Think it is good / best for the group?
Having seen the options and individual preferences
Having seen the reactions of the group members?
What is the problem with this?
![Page 19: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/19.jpg)
Metrics (5)
Extent to which the recommendations correspond to
• What groups would decide themselves?• What human facilitators would decide for the
group?
What is the problem with this?
![Page 20: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/20.jpg)
How to obtain groups for evaluation?
• Artificially construct groups – From existing data about individuals– Or: of invented individuals
• Use real groups:– But without group data– Or: to generate group data
(e.g. What the group decides to watch when together)
– Or: to provide recommendations and measure effect
![Page 21: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/21.jpg)
Groups matter
• Group size
• Homogeneity in opinions in group
• And many other attributes (discussed later)
![Page 22: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/22.jpg)
Domains matter
Music
Tourist attractions
NewsRestaurants / Food
Why do they matter?
![Page 23: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/23.jpg)
Exp1: What do people do?
Compare what people do with what strategies do
I know individual ratings of Peter, Mary,
and Jane. What to recommend to the
group? If time to watch 1-2-3-4-5-6-7 clips…
Why?
![Page 24: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/24.jpg)
Exp1: Results
• Participants do ‘use’ some of the strategies• Care about Misery, Fairness, Preventing
starvation
![Page 25: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/25.jpg)
Exp2: What do people like?
You know the individual ratings of you and your
two friends. I have decided to show you the
following sequence. How satisfied would you be?
And your friends?
Why?
Which strategy does best?Which prediction function does best?
![Page 26: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/26.jpg)
Exp2: Results
• Multiplicative strategy performs best (FEHJDI is the only sequence that has ratings 4 for all subjects for all individuals)
• Prediction functions: Some evidence of normalization, Misery taken into account, Quadratic is better than linear
![Page 27: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/27.jpg)
Evaluation of aggregation strategies (1)
• Our work: Best Multiplicative (from Exp 2 above and simulations with satisfaction functions below)
• Unfortunatly, Multiplicative often not investigated, indicated the ones that did in blue
• Where it was included, it performed best
![Page 28: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/28.jpg)
Evaluation of aggregation strategies
• Senot et al (2010): TV, historic TV use (individual and group data), size 2-5, Best: Average most groups, Dictatorship 20% of groups
• Carvalho & Macedo (2013): MovieLens data, Average metric, size 3-7, Best: Average
• Bourke et al (2011): TV movies, User study, Average metric, size 3-10, Best: Multiplicative
• De Pessemier et al (2013): Movies, Synthetic data, Average metric, size 2-5, Best: Average and Average without Misery
![Page 29: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/29.jpg)
Evaluation of aggregation strategies (3)
• Baltrunas et al (2010): MovieLens data, Weighted average metric, Size 2-8, Average, Borda, Least Misery, Spearman footrule very similar
• Berkovsky & Freyne (2010): Recipes, User study, Size 2-4, Best: Weighted average (only compared to Average)
• Salamo et al (2012): Holidays, Synthetic groups, Average metric, Size 3-8, Best: Multiplicative, Borda, Completeness
![Page 30: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/30.jpg)
Challenge 2: Recommending
Sequences
![Page 31: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/31.jpg)
Why sequences?
• Sequences for groups are a lot more interesting than individual items
• With a sequence, it is harder to please everybody
• Fairness has a larger role• Example domains:
tourist attractions, music in shop, TV news
![Page 32: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/32.jpg)
How to deal with order?
Determine Group List
Show items in the order of the list
Determine top N items to show
Determine Group List
Determine order to show items in
Determine top N items to show
Show items in that order
Determine Group List
UpdateRatings
Show first item of list
Time left
But: mood consistency, strong ending, narrative flow,..
But: given all this, perhaps other items are more suitable..
![Page 33: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/33.jpg)
Exp3: Effect of mood, topic
How much would you want to watch these 7 news items?
How would they make you feel?
[Insert name of your favorite sport’s club] wins important game,Fleet of limos for Jennifer Lopez 100-metre trip,Heart disease could be halved, Is there room for God in Europe?,Earthquake hits Bulgaria, UK fire strike continues,Main three Bulgarian players injured after Bulgaria-Spain football match
The first item on the news is “England football team has to play Bulgaria”. Rate interest, resulting mood.
Rate interest in 7 news items again
![Page 34: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/34.jpg)
Exp3: Results
• Mood can influence ratings• Topical relatedness can influence ratings• Effect of topical relatedness can depend on
rating for first item (if interested then more likely to increase)
• Importance dimension
![Page 35: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/35.jpg)
Domain specific aspects of sequences
For example, in tourist guide domain:• Mutually exclusive / hard to combine items• Physical proximity • Diversity concerns
In news domain:• Novelty concerns• Topical relatedness
How about music?
![Page 36: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/36.jpg)
Challenge 3:
Modelling Satisfaction
![Page 37: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/37.jpg)
Why model satisfaction?
• When adapting to a group of people, you cannot give everyone what they like all the time
• But you don’t want somebody to get too dissatisfied…
• When adapting a sequence to an individual, the order may impact satisfaction
![Page 38: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/38.jpg)
Strategies that use satisfaction
,
,
,
Know how satisfied each user is with the items so far
And their profile
B C H I J
9 8 9 3 8
5 2 6 7 6
4 3 8 10 8
Decide which item to present next, trying to please the least satisfied user
![Page 39: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/39.jpg)
Strongly support grumpiest strategy
• Pick item most liked by the least satisfied person
• If multiple items most liked, use existing strategy (e.g. Multiplicative) to choose between them
Problem: Suppose Mary least satisfied so far - Strategy would pick A - Very bad for Jane - Better to show E?
A B D E
Peter 10 4 6 10
Jane 1 9 9 7
Mary 10 5 7 9
![Page 40: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/40.jpg)
Alternative strategies using satisfaction
• Weakly support grumpiest strategy– Consider all items quite liked (say rating>7) by the
least satisfied person– Use existing strategy to choose between them
• Strategies using weights– Assign weights to users depending on satisfaction– Use weighted form of existing strategy, e.g.
weighted Average– Cannot be done with some strategies, such as
Least Misery
![Page 41: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/41.jpg)
Challenge is to model satisfaction
• Would like a model that predicts satisfaction of an individual userafter a sequence of items
![Page 42: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/42.jpg)
Basic model
![Page 43: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/43.jpg)
Impact
Quadratic(Rebalanced(
Normalized(Rating( )))
![Page 44: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/44.jpg)
Variant 1: Satisfaction decreases over time
x
0 1 =0: No memory =1: Perfect memory
![Page 45: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/45.jpg)
Variant 2: Satisfaction is bounded
x
(1+)
![Page 46: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/46.jpg)
Mood impacts evaluative judgement
How often has your television broken down in the last years?
Hardly ever.
A lot!
Isen et al, 1978
![Page 47: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/47.jpg)
Mood impacts evaluative judgement
How much have you
been persuaded?
A little.
A lot.
Mackie & Worth, 1989
![Page 48: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/48.jpg)
Affective forecasting can change actual emotional experience
I really hate it..
It is ok.I am expecting to
like this…
I am expecting to hate this…
Assimilation
Wilson & Klaaren, 1992
![Page 49: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/49.jpg)
Variant 3: Impact depends on mood
x
x
,
![Page 50: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/50.jpg)
Impact depends on mood
,
x ( )
0 1 =0: No impact mood =1: Mood determines all
![Page 51: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/51.jpg)
Variant 4: Combination of Variants 2 and 3
x
x
,
(1+)
![Page 52: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/52.jpg)
Evaluation by simulation
-20
0
20
40
60
Jane, sequence from Multiplicative strategy
0
10
20
30
40
50
60
70
0 0.2 0.4 0.6 0.8 0.9 1
0
10
20
30
40
50
60
70
0 0.2 0.4 0.6 0.8 0.9 1
-10
-5
0
5
10
15
Variant 1 Variant 2
=
• Models predict how satisfied Peter, Jane, Mary would be with a sequence of items
• If we know , …• UM05 contains 54
prediction graphs• Compare these to
predictions by humans (from Exp 2)
![Page 53: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/53.jpg)
Simulation results
• Some strategies result in misery for any
• Variant 2 predicts misery for the Average strategy, contradicting our subjects
• Value of should be high (>0.5)• With high , Multiplicative performed best
• Lower values of might be better
![Page 54: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/54.jpg)
Inherent complexity of evaluation
Evaluation challenge of EAS workshop at UM05
• Need accurate ratings which is hard due to order effect
• Need to know satisfaction after each item• Items should be ‘unrelated’ and preferably not have
emotional content
Initial empirical evaluation has been done, using an educational task
![Page 55: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/55.jpg)
Exp 4: Which model is best?
• Three lexical decision tasks:
• Subjects split into two groups:Group A: Easy – Hard – MediumGroup B: Hard – Easy – Medium
• Self-reported satisfaction with performance on task, and over all tasks so far
Is this an English word? (2s to answer)
Easy Medium Hard
Women PhialDebut
![Page 56: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/56.jpg)
Exp4: Results
-4
-2
0
2
4
6
8
10
1 2 3
Group A
Group B
Satisfaction with overall performance after each task
Variants 1 and 2 predict lower satisfaction for group B (easy first) after 2 tasks, due to emotions wearing off.
Assimilation could result in higher satisfaction for B.
Comparison with individual task satisfaction, shows more like averaging.
Variant 4 is best?? Task number
![Page 57: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/57.jpg)
Exp4: Results (2)
• Analysed Error Rates of best fit to data of Variants 2 and 4
• Variant 2 fitted the data rather badly• Variant 4 was a lot better, so assimilation parameter
ε helps• Found individual differences in δ and ε
(as expected)
![Page 58: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/58.jpg)
Emotional contagion
Totterdell et al, 1998; Barsade 2002; Bartel & Saavedra, 2000
![Page 59: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/59.jpg)
Emotional contagion
Totterdell et al, 1998; Barsade 2002; Bartel & Saavedra, 2000
![Page 60: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/60.jpg)
Emotional contagion
Totterdell et al, 1998; Barsade 2002; Bartel & Saavedra, 2000
![Page 61: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/61.jpg)
Emotional contagion
, x
Or x -
![Page 62: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/62.jpg)
Susceptibility of emotional contagion
User Dependent
So, should be user dependent
Laird et al, 1994
![Page 63: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/63.jpg)
Types of relationship
Authority Ranking
Market PricingEquality Matching
“Somebody you respect highly”
“Somebody you do deals with / compete with”
“Somebody you share everything with, e.g. a best friend”
Communal Sharing
“Somebody you are on equal footing with”
Fiske, 1992; Haslam, 1994
![Page 64: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/64.jpg)
Susceptibility and types of relationship
=
When calculating of by
Need to take account of ’s susceptibility
And the relationship between and
![Page 65: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/65.jpg)
Exp5: Emotional contagion
• Susceptibility to emotional contagion measured using existing scale (Doherty, 1997)
• “Think of somebody [relationship type]. Assume you and this person are watching TV together. You are enjoying the program a little. How would it make you feel to know that the other person is [enjoying it greatly / really hating it]? My enjoyment would…”
• We expect Authority Ranking and Communal Sharing to have more contagion.
• Will Market Pricing have negative ?
![Page 66: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/66.jpg)
Exp5: Results
• Contagion happens• More contagion for Authority Ranking and
Communal Sharing relationships• No difference between negative and positive
contagion• Susceptibility only seemed to make a difference for
Communal Sharing relationships
![Page 67: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/67.jpg)
Challenge 4: Incorporating Group
Attributes
![Page 68: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/68.jpg)
What attributes matter?
• Remember the task I gave you at the start
• What attributes of the people in your group influenced the decion making (excluding their opinions on the music items)?
• Or could have influenced the decision making if they had beeen present in your group
![Page 69: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/69.jpg)
Attributes of group members
• Demographics and roles [Ardissono et al, 2002; Senot et al, 2010]
• Personality– Propensity to emotional contagion – Agreeableness?– Assertiveness and cooperativeness
[Quijano-Sanchez et al, 2013]
• Expertise [Berkovsky & Freyne; Gatrell et al, 2010, Herr et al, 2012]
• Personal impact/cognitive centrality [Liu et al, 2012; Herr et al, 2012]
Typically used to vary the weights of group members
![Page 70: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/70.jpg)
Attributes of the group as a whole
• Relationship strengthGatrell et al (2010) propose:
Most Pleasure for strong relations, Least Misery for weak, Average for intermediate
• Relationship type:Wang et al (2010) distinguish:– Positionally homogeneous vs heterogenous groups– Tightly coupled versus loosly coupled groups
Typically used to select a different strategy
![Page 71: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/71.jpg)
Attributes of pairs in the group
• Relationship strength/social trust [Quijano-Sanchez et al, 2013]
• Personal impact[Liu et al, 2012; Ye et al, 2012, Ioannidis et al, 2013]
Typically used to adjust the ratings of an individual in light of the ratings of the other person in the pair.
![Page 72: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/72.jpg)
Challenge 5: Explaining Group
Recommendations
![Page 73: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/73.jpg)
Improve:– Trust– Effectiveness– Persuasiveness– Efficiency– Transparency– Scrutability– Satisfaction
[Tintarev & Masthoff]
And these aims can conflict
Aim of explanations in any rec sys
Explanations may be even more important in group recommender systems
Which aims?
![Page 74: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/74.jpg)
Sequence issue
• More work is needed on explaining sequences, particularly sequences that contain items the user will not like
![Page 75: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/75.jpg)
Privacy issue
• Many aims may require explanations that reflect on other group members….
• How to do this without disclosing sensitive information?
• Even general statements such as “this item was not chosen as it was hated by somebody in your group” may cause problems
![Page 76: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/76.jpg)
Conclusion
Many challenges
Needs a lot more work
![Page 77: Research Challenges in Group Recommender Systems Judith Masthoff](https://reader036.vdocument.in/reader036/viewer/2022062322/5697bfa81a28abf838c997d8/html5/thumbnails/77.jpg)
Questions ?