A Multimedia Interface for Facilitating
Comparisons of Opinions
                      Lucas Rizoli
           Supervisor G...
Opinion data is
  abundant and useful,
  but analysis is expensive and difficult




                                     ...
Our interface
  supports analysis of opinion data,
  particularly comparison across entities




                         ...
It supports analysis by
  visualizing the data and
  summarizing notable comparisons




                                 ...
Our user study shows
  the visualization is usable,
  the summarizer’s choices are human-like




                        ...
6
Text mining
(Carenini, Ng, & E. Zwart, 2006)




                                   7
8
9
10
11
12
+2    +1




 +2        –3




                13
Spore


       Gameplay       Technology           DRM

Creature creation    Graphics
Cell phase           Sound
Civilizat...
vs.




      15
16
Applications
●   Consumers
●   Intelligence
    –   Competitive analysis
    –   Forecasts
●   Research
    –   Survey, qu...
18
19
Controversiality
  (Carenini & Cheung, 2008)




                              20
21
22
23
(Dis)similarity of comparisons
●   Adapt stats to pairs of distributions
●   Aspects of a comparison
    –   counts
    – ...
25
26
27
28
29
30
31
32
33
34
Interpreting aspects
●   Aspects in range 0–1
●   Interpretation
    –   means 0.6 != contros 0.6 != dists 0.6




       ...
36
37
Selecting comparisons
1. Filter out low-count comparisons
2. Rank by # of extreme aspects (VD, VS)
3. Realize top comparis...
39
Study goals
●   Evaluate content selection strategy
    –   Matches human selections?
         ●   Better than baseline?
 ...
41
42
Baseline selection strategies
●   Naïve
    –   Randomly select which and how many
●   Semi-informed
    –   Likely select...
Matches human selections?




                            44
Humans like selections?



      0.500   0.449   0.454




                              45
Humans like selections?



                  0.500      0.449    0.454
●   Roughly 20% difference
●   60% of system select...
Usability




            47
Opinion data is
   abundant and useful,
   but analysis is expensive and difficult


Our interface
   supports analysis of...
Thank you




            49
Future work
●   Tune thresholds and aspects
●   Analysis of human reasoning
●   Machine learning for selection




       ...
Future work
●   More evaluation of visualization
    –   Interaction
    –   Deeper heirarchies
    –   Different data
   ...
Future work
●   Machine learning–based selection
    –   Trained on study data
    –   Which
         ●   Regression on co...
Sentence construction
●   Always main claim: counts
●   All other aspects relate to counts
    –   Support: same (dis)simi...
counts
                     rt




                          co
                   o
              pp




                ...
counts
                     rt




                          co
                   o
              pp




                ...
counts
                   rt




                        co
                 o
            pp




                        ...
Study
●   36 subjects
    –   24 female
    –   19–43 years old
●   22 different pairs of entities
    –   Subjects saw ~4...
Data generation
●   No existing dataset
●   Generated similar to existing datasets
    –   Distribution, modality
●   Expl...
Generated data
●   Generic camera features
    –   Consistent with scenario
●   Simple heirarchy
    –   Reduce visual and...
Generated data
●   9 comparison types
    –   Constraints on aspects
    –   Range of support/contrast
●   22 summary case...
61
62
63
64
65
66
67
68
69
70
71
72
73
74
Upcoming SlideShare
Loading in …5
×

A Multimedia Interface For Facilitating Comparisons Of Opinions (Thesis Presentation)

1,003 views

Published on

Slide deck used to present and defend my master's thesis project. The project is detailed in a paper published in the Proceedings of the 2009 Conference on Intelligent User Interfaces (http://doi.acm.org/10.1145/1502650.1502696).

Published in: Design
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total views
1,003
On SlideShare
0
From Embeds
0
Number of Embeds
8
Actions
Shares
0
Downloads
10
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

A Multimedia Interface For Facilitating Comparisons Of Opinions (Thesis Presentation)

  1. 1. A Multimedia Interface for Facilitating Comparisons of Opinions Lucas Rizoli Supervisor Giuseppe Carenini University of British Columbia February 11, 2009
  2. 2. Opinion data is abundant and useful, but analysis is expensive and difficult 2
  3. 3. Our interface supports analysis of opinion data, particularly comparison across entities 3
  4. 4. It supports analysis by visualizing the data and summarizing notable comparisons 4
  5. 5. Our user study shows the visualization is usable, the summarizer’s choices are human-like 5
  6. 6. 6
  7. 7. Text mining (Carenini, Ng, & E. Zwart, 2006) 7
  8. 8. 8
  9. 9. 9
  10. 10. 10
  11. 11. 11
  12. 12. 12
  13. 13. +2 +1 +2 –3 13
  14. 14. Spore Gameplay Technology DRM Creature creation Graphics Cell phase Sound Civilization phase System requirements 14
  15. 15. vs. 15
  16. 16. 16
  17. 17. Applications ● Consumers ● Intelligence – Competitive analysis – Forecasts ● Research – Survey, questionnaire 17
  18. 18. 18
  19. 19. 19
  20. 20. Controversiality (Carenini & Cheung, 2008) 20
  21. 21. 21
  22. 22. 22
  23. 23. 23
  24. 24. (Dis)similarity of comparisons ● Adapt stats to pairs of distributions ● Aspects of a comparison – counts – means – contros – dists 24
  25. 25. 25
  26. 26. 26
  27. 27. 27
  28. 28. 28
  29. 29. 29
  30. 30. 30
  31. 31. 31
  32. 32. 32
  33. 33. 33
  34. 34. 34
  35. 35. Interpreting aspects ● Aspects in range 0–1 ● Interpretation – means 0.6 != contros 0.6 != dists 0.6 35
  36. 36. 36
  37. 37. 37
  38. 38. Selecting comparisons 1. Filter out low-count comparisons 2. Rank by # of extreme aspects (VD, VS) 3. Realize top comparisons • Sentence templates 38
  39. 39. 39
  40. 40. Study goals ● Evaluate content selection strategy – Matches human selections? ● Better than baseline? – Humans like selections? ● Usability of visualization 40
  41. 41. 41
  42. 42. 42
  43. 43. Baseline selection strategies ● Naïve – Randomly select which and how many ● Semi-informed – Likely select same how many as subjects – Randomly select which 43
  44. 44. Matches human selections? 44
  45. 45. Humans like selections? 0.500 0.449 0.454 45
  46. 46. Humans like selections? 0.500 0.449 0.454 ● Roughly 20% difference ● 60% of system selections marked as “good” 46
  47. 47. Usability 47
  48. 48. Opinion data is abundant and useful, but analysis is expensive and difficult Our interface supports analysis of opinion data, particularly comparison across entities, by visualizing the data and summarizing notable comparisons Our user study shows the visualization is usable, the summarizer’s choices are human-like 48
  49. 49. Thank you 49
  50. 50. Future work ● Tune thresholds and aspects ● Analysis of human reasoning ● Machine learning for selection 50
  51. 51. Future work ● More evaluation of visualization – Interaction – Deeper heirarchies – Different data – Insight ● Multiple entities ● Improved summarization – Visual cues 51
  52. 52. Future work ● Machine learning–based selection – Trained on study data – Which ● Regression on comparison selection scores – How many ● Max # of comparisons (2) 52
  53. 53. Sentence construction ● Always main claim: counts ● All other aspects relate to counts – Support: same (dis)similarity as counts – Contrast: different ● Always mention means ● Mention contros, dists when they are extreme 53
  54. 54. counts rt co o pp nt u ra s st means contros dists 54
  55. 55. counts rt co o pp nt u ra s st means contros dists 55
  56. 56. counts rt co o pp nt u ra s st contros means 56
  57. 57. Study ● 36 subjects – 24 female – 19–43 years old ● 22 different pairs of entities – Subjects saw ~4 each 57
  58. 58. Data generation ● No existing dataset ● Generated similar to existing datasets – Distribution, modality ● Explore space of possible data – Too large – Representative of larger space 58
  59. 59. Generated data ● Generic camera features – Consistent with scenario ● Simple heirarchy – Reduce visual and task complication 59
  60. 60. Generated data ● 9 comparison types – Constraints on aspects – Range of support/contrast ● 22 summary cases – Summaries by type – Range of ● overall, ● how many, ● which, ● others. 60
  61. 61. 61
  62. 62. 62
  63. 63. 63
  64. 64. 64
  65. 65. 65
  66. 66. 66
  67. 67. 67
  68. 68. 68
  69. 69. 69
  70. 70. 70
  71. 71. 71
  72. 72. 72
  73. 73. 73
  74. 74. 74

×