Coupling Story to Visualization: Using Textual Analysis as a Bridge - - PowerPoint PPT Presentation

▶
coupling story to visualization using textual analysis as
SMART_READER_LITE
LIVE PREVIEW

Coupling Story to Visualization: Using Textual Analysis as a Bridge - - PowerPoint PPT Presentation

Aug 31, 2022 225 likes •635 views

Coupling Story to Visualization: Using Textual Analysis as a Bridge Between Data and Interpretation Ronald Metoyer, Qiyu Zhi , Bart Janczuk, Walter Scheirer University of Notre Dame 1 2 3 4 Narrative Text + Visual Evidence

slide-1
SLIDE 1

Coupling Story to Visualization: Using Textual Analysis as a Bridge Between Data and Interpretation

Ronald Metoyer, Qiyu Zhi, Bart Janczuk, Walter Scheirer University of Notre Dame

  • 1
slide-2
SLIDE 2

2

slide-3
SLIDE 3

3

slide-4
SLIDE 4

4

slide-5
SLIDE 5

Narrative Text Visual Evidence +

5

slide-6
SLIDE 6

Narrative Text Visual Evidence

6

From http://www.espn.com/nba/

slide-7
SLIDE 7

Narrative Text

Visual Evidence

7

https://www.nytimes.com/interactive/2017/01/30/us/politics/trump-immigration-ban-demographics.html

slide-8
SLIDE 8

Integrating narrative text with visual evidence is widely used.

8

slide-9
SLIDE 9

Narrative text and visual evidence are often independently presented.

9

slide-10
SLIDE 10

10

http://www.espn.com/nba/game?gameId=400975463

slide-11
SLIDE 11

Limitations:

Interpret the narrative in context Interpret the story from visualization

11

slide-12
SLIDE 12

Narrative Text Visual Evidence

12

slide-13
SLIDE 13

Deep coupling of narrative text and visualization

13

slide-14
SLIDE 14

Deep coupling of narrative text and visualization

14

slide-15
SLIDE 15

Identifying Story Elements

Who

Story

Where What When

15

slide-16
SLIDE 16

Identifying Story Elements

Who

Story

When What Where

16

slide-17
SLIDE 17

Identifying Story Elements

Who

Story

When What Where

17

slide-18
SLIDE 18

Identifying Story Elements

Who

Story

When What Where

18

slide-19
SLIDE 19

Identifying Story Elements

Who

Story

When What Where

19

slide-20
SLIDE 20

The Warriors trailed by six with three minutes left before Durant, criticized for leaving Oklahoma City last summer to chase a championship, brought them back, scoring 14 in the paint.

Identifying Story Elements

Who What When Where

20

slide-21
SLIDE 21

Identifying Story Elements: Who

Named Entity Recognition (NER) and existing database for team name, player name, coach name, referees in the league

21

slide-22
SLIDE 22

Identifying Story Elements: When and Where

Regular Expression and Grammar Rules

22

slide-23
SLIDE 23

Identifying Story Elements: What

Labeled sentences from 13 story posts SVM Classifier 98% accuracy on 150 test sentences

23

Story Grammar

slide-24
SLIDE 24

Identifying Story Elements: What

Labeled sentences from 13 story posts SVM Classifier 98% accuracy on 150 test sentences

24

Story Grammar

slide-25
SLIDE 25

Identifying Story Elements: What

Labeled sentences from 13 story posts SVM Classifier 98% accuracy on 150 test sentences

25

Story Grammar

slide-26
SLIDE 26

Identifying Story Elements: What

Labeled sentences from 13 story posts SVM Classifier 98% accuracy on 150 test sentences

26

Story Grammar

slide-27
SLIDE 27

Deep coupling of narrative text and visualization

27

slide-28
SLIDE 28

Interaction Design: narrative text to visual element

28

slide-29
SLIDE 29

Interaction Design: visual element to narrative text

29

slide-30
SLIDE 30

Interaction Design: linking visual elements

30

slide-31
SLIDE 31

Case Study

Domain expert with 5 years experience as a media producer

31

slide-32
SLIDE 32

Case Study

“I love the idea of being able to experience the article, but really dial-in on a specific part of it myself”

32

slide-33
SLIDE 33

“If the writer emphasized the number of points Curry had from the paint, I’d be interested in seeing that visually, and also exploring for myself where else he may have scored from.”

Case Study

33

slide-34
SLIDE 34

“It would be useful if the text highlighted the types of elements - player, stats, times, etc., with different colors”

Case Study

34

slide-35
SLIDE 35

Create exploratory interaction mechanisms for readers.

Implications

35

  • More granular analysis
  • Social media
slide-36
SLIDE 36

Reinforce author communication for writers.

Implications

36

  • Fact checking
  • Idea generation
slide-37
SLIDE 37

Discussion

37

  • Generalizability
  • Evaluation
slide-38
SLIDE 38

We have presented a novel approach to automatically couple narrative text to visualizations for data-rich stories and demonstrated the approach in the basketball story domain.

Conclusion

38

slide-39
SLIDE 39

Coupling Story to Visualization: Using Textual Analysis as a Bridge Between Data and Interpretation

Ronald Metoyer, Qiyu Zhi, Bart Janczuk, Walter Scheirer University of Notre Dame

Questions?

  • 39

@nickyzhi123 qzhi@nd.edu @职启予Nicky