[PPT] - Explaining rankings Maartje ter Hoeve University of Amsterdam & PowerPoint Presentation

SLIDE 1

Explaining rankings

Maartje ter Hoeve University of Amsterdam & Blendle Maartje ter Hoeve maartje.terhoeve@student.uva.nl

SLIDE 2

C o n t e n t

Maartje ter Hoeve maartje.terhoeve@student.uva.nl What and why? Rankings Research questions Related work Answering research questions Discussion and Conclusion Blendle

SLIDE 3

C o n t e n t

Maartje ter Hoeve maartje.terhoeve@student.uva.nl What and why? Rankings Research questions Related work Answering research questions Discussion and conclusion Blendle

SLIDE 4

I n t r o d u c t i o n

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

What is explainability and why is it needed?

SLIDE 5

E x p l a i n a b i l i t y : w h a t a n d w h y ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl Model

SLIDE 6

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

?

E x p l a i n a b i l i t y : w h a t a n d w h y ?

SLIDE 7

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

E x p l a i n a b i l i t y : w h a t a n d w h y ?

SLIDE 8

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

User Developer

E x p l a i n a b i l i t y : w h a t a n d w h y ?

SLIDE 9

B u t w h a t i s a n e x p l a n a t i o n ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

An explanation needs to faithfully give the underlying cause of an event

SLIDE 10

B u t w h a t i s a n e x p l a n a t i o n ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

Justification Provide conceptual explanations that do not necessarily expose the underlying structure of the algorithm Description Provide conceptual explanations that do expose the underlying structure of the algorithm

SLIDE 11

C o n t e n t

Maartje ter Hoeve maartje.terhoeve@student.uva.nl What and why? Rankings Research questions Related work Answering research questions Discussion and conclusion Blendle

SLIDE 12

R a n k i n g s

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

1 2 3 n - 1 n 4 n - 2

SLIDE 13

H o w d o w e e x p l a i n a r a n k i n g ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

231 203 1 157 6 228 3 543 398 2 231 8 432 4 Only looking at the score of an item is not sufficient

SLIDE 14

C o n t e n t

Maartje ter Hoeve maartje.terhoeve@student.uva.nl What and why? Rankings Research questions Related work Answering research questions Discussion and conclusion Blendle

SLIDE 15

B l e n d l e

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

SLIDE 16

B l e n d l e

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

Blendle already has heuristic justifications We use these as one of our baselines

SLIDE 17

C o n t e n t

Maartje ter Hoeve maartje.terhoeve@student.uva.nl What and why? Rankings Research questions Related work Answering research questions Discussion and conclusion Blendle

SLIDE 18

R e s e a r c h q u e s t i o n s

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

RQ2 What way of showing news recommendations reasons do users prefer: textual or visual reasons; a single reason or multiple reasons; apparent or less apparent reasons?

PART 1

RQ1 Do users want to receive explanations of why particular news items are recommended to them?

SLIDE 19

R e s e a r c h q u e s t i o n s

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

RQ3 How do we provide users with easy to understand, uncluttered, listwise explanations? RQ4 How do we build an explanation system that produces faithful, model-agnostic explanations for the outcome of a ranking algorithm, yet is scalable so that it can run in real time? RQ5 Does the reading behaviour of users who are provided with model-agnostic listwise explanations for a personalized ranked selection of news articles differ from the reading behaviour of users who are provided with heuristic or pointwise explanations for a personalized ranked selection of news articles?

PART 2

SLIDE 20

C o n t e n t

Maartje ter Hoeve maartje.terhoeve@student.uva.nl What and why? Rankings Research questions Related work Answering research questions Discussion and conclusion Blendle

SLIDE 21

R e l a t e d w o r k

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

LIME (Ribeiro et al, 2016): find a local, faithful explanation for the decision of any classifier

LIME is a baseline of this research We work with rankings, not classifiers Therefore we bin our ranking scores mLIME

SLIDE 22

C o n t e n t

Maartje ter Hoeve maartje.terhoeve@student.uva.nl What and why? Rankings Research questions Related work Answering research questions Discussion and conclusion Blendle

SLIDE 23

P a r t 1 - U s e r s t u d y

Single Reason - Visible Single Reason - Invisible Multiple Reasons - Visible Multiple Reasons - Combined Bar chart 179 sent type 1 180 sent type 2 182 sent type 3

1 2 3

41 answered type 1 36 answered type 2 43 answered type 3

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

SLIDE 24

R Q 1 D o u s e r s w a n t e x p l a n a t i o n s ?

User wants reasons Times answered Yes 65 Somewhat 24 No 26 I don't know 5 X2 = 14.55, p < 0.001

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

SLIDE 25

Single Reason - Visible Single Reason - Invisible Multiple Reasons - Visible Multiple Reasons - Combined Bar chart

R Q 2 P r e f e r e n c e s h o w e x p l a n a t i o n s a r e s h o w n ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

SLIDE 26

R Q 2 P r e f e r e n c e s h o w e x p l a n a t i o n s a r e s h o w n ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

Transparency Sufficiency Trust Satisfaction

SLIDE 27

P a r t 2

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

SLIDE 28

R Q 3 H o w d o w e m a k e l i s t w i s e e x p l a n a t i o n s ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

231 203 1 157 6 228 3 543 398 2 231 8 432 4 Explain the entire list? Explain items in comparison to other items? Explain which features were important for the position in the ranking?

SLIDE 29

R Q 3 H o w d o w e m a k e l i s t w i s e e x p l a n a t i o n s ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

231 203 1 157 6 228 3 543 398 2 231 8 432 4 Explain the entire list? Explain items in comparison to other items? Explain which features were important for the position in the ranking?

SLIDE 30

Maartje ter Hoeve maartje.terhoeve@student.uva.nl f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4

Which features are most important for the item's position in the ranking?

R Q 3 H o w d o w e m a k e l i s t w i s e e x p l a n a t i o n s ?

SLIDE 31

R Q 4 H o w d o w e d e s i g n t h i s ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

Main intuition If we change feature values and the ranking changes, then this feature was important

SLIDE 32

R Q 4 H o w d o w e d e s i g n t h i s ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

Training phase Find how feature values change the ranking Find disruptive distributions and points of interests Use distributions to sample feature values from Find most important features Return most important features as explanations Explaining phase

LISTEN - LISTwise ExplaiNer

SLIDE 33

R Q 4 H o w d o w e d e s i g n t h i s ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

Training phase

SLIDE 34

R Q 4 H o w d o w e d e s i g n t h i s ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4

200 160 120 100 180

Find how feature values change the ranking: f0 [1, 2, 3, 4, 5, 6]

SLIDE 35

R Q 4 H o w d o w e d e s i g n t h i s ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4

200 160 120 100

f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 1 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4

180 200 90 120 100 180

Find how feature values change the ranking: f0 [1, 2, 3, 4, 5, 6]

SLIDE 36

R Q 4 H o w d o w e d e s i g n t h i s ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4

200 160 120 100

f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 2 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4

180 200 110 120 100 180

Find how feature values change the ranking: f0 [1, 2, 3, 4, 5, 6]

SLIDE 37

R Q 4 H o w d o w e d e s i g n t h i s ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4

200 160 120 100

f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 3 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4

180 200 160 120 100 180

Find how feature values change the ranking: f0 [1, 2, 3, 4, 5, 6]

SLIDE 38

R Q 4 H o w d o w e d e s i g n t h i s ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4

200 160 120 100

f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 4 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4

180 200 170 120 100 180

Find how feature values change the ranking: f0 [1, 2, 3, 4, 5, 6]

SLIDE 39

R Q 4 H o w d o w e d e s i g n t h i s ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4

200 160 120 100

f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 5 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4

180 200 190 120 100 180

Find how feature values change the ranking: f0 [1, 2, 3, 4, 5, 6]

SLIDE 40

R Q 4 H o w d o w e d e s i g n t h i s ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4

200 160 120 100

f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 6 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4

180 200 195 120 100 180

Find how feature values change the ranking: f0 [1, 2, 3, 4, 5, 6]

SLIDE 41

R Q 4 H o w d o w e d e s i g n t h i s ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

Find disruptive distributions and points of interests

SLIDE 42

R Q 4 H o w d o w e d e s i g n t h i s ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

Explanation phase

SLIDE 43

R Q 4 H o w d o w e d e s i g n t h i s ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

Find most important features

f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4

200 160 120 100

f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4

180 170 160 120 100 180

SLIDE 44

R Q 4 H o w d o w e d e s i g n t h i s ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4 f0 f1 f2 f3 f4

Return most important features

SLIDE 45

R Q 4 H o w d o w e d e s i g n t h i s ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

Is this faithful? Construct dummy data where we know what to expect LISTEN gives the correct results Disruptive distribution approach slightly decreases faithfulness, yet increases speed

SLIDE 46

R Q 4 H o w d o w e d e s i g n t h i s ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

This is still not fast enough to run in production

f0 f1 f2 …. fn-1 fn f0 f1 f2 …. fn-1 fn f0 f1 f2 …. fn-1 fn f0 f1 f2 …. fn-1 fn f0 f1 f2 …. fn-1 fn f0 f1 f2 …. fn-1 fn

Q-LISTEN

SLIDE 47

R Q 4 H o w d o w e d e s i g n t h i s ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

Same holds for mLIME Q-mLIME

f0 f1

. .

fn f0 f1

. .

fn

SLIDE 48

R Q 5 H o w d o u s e r s b e h a v e ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

A. Heuristic

A/B/C - test

B. Q-mLIME
C. Q-LISTEN

SLIDE 49

R Q 5 H o w d o u s e r s b e h a v e ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

SLIDE 50

R Q 5 H o w d o u s e r s b e h a v e ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

Results

SLIDE 51

R Q 5 H o w d o u s e r s b e h a v e ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

Results

Heuristic Q-mLIME Q-LISTEN % reasons seen (of total reads) 3.55 3.54 3.51 % reasons seen (of total reasons) 34.1 32.9 32.0 Reasons per user (of users that see reasons) 1.83 1.86 1.72 Article opened within 2 minutes (% of all reasons seen) 12.1 12.9 10.6 Reasons seen after 20 minutes of opening (% of all reasons seen) 11.0 10.1 10.7

SLIDE 52

C o n t e n t

Maartje ter Hoeve maartje.terhoeve@student.uva.nl What and why? Rankings Research questions Related work Answering research questions Discussion and conclusion Blendle

SLIDE 53

C o n c l u s i o n a n d d i s c u s s i o n

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

RQ1 Do users want to receive explanations of why particular news items are recommended to them? RQ2 What way of showing news recommendations reasons do users prefer: textual or visual reasons; a single reason or multiple reasons; apparent or less apparent reasons?

PART 1

Yes No specific one

SLIDE 54

C o n c l u s i o n a n d d i s c u s s i o n

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

RQ3 How do we provide users with easy to understand, uncluttered, listwise explanations? RQ4 How do we build an explanation system that produces faithful, model-agnostic explanations for the outcome of a ranking algorithm, yet is scalable so that it can run in real time?

PART 2

We look at which features were most important for an item's position in the ranking We find feature importance by changing the feature values and changing the rankings We make disruptive distributions We learn the explanation space with a neural net

SLIDE 55

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

RQ5 Does the reading behaviour of users who are provided with model-agnostic listwise explanations for a personalized ranked selection of news articles differ from the reading behaviour of users who are provided with heuristic or pointwise explanations for a personalized ranked selection of news articles?

C o n c l u s i o n a n d d i s c u s s i o n

We do not find any significant differences

SLIDE 56

C o n c l u s i o n a n d d i s c u s s i o n

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

Take home message Users clearly state that they want explanations. Therefore, even though their behaviour is not affected by the explanations, still provide them with faithful explanations

SLIDE 57

R e a s o n s s e e n

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

SLIDE 58

L o s s a n d a c c u r a c y c u r v e s

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

SLIDE 59

m L I M E v s L I S T E N

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

SLIDE 60

A c t i v e a n d l e s s a c t i v e u s e r s

Maartje ter Hoeve maartje.terhoeve@student.uva.nl

SLIDE 61

R Q 5 H o w d o u s e r s b e h a v e ?

Maartje ter Hoeve maartje.terhoeve@student.uva.nl