summarizing archival collections using storytelling techniques

Post on 14-Jan-2017

1.187 Views

Category:

Technology

0 Downloads

Preview:

Click to see full reader

TRANSCRIPT

Summarizing archival collections using storytelling techniques

Yasmin AlNoamanyMichele C. WeigleMichael L. Nelson

Old Dominion UniversityWeb Science & Digital Libraries Research Group

www.cs.odu.edu/~mln/@phonedude_mln

Research Funded by IMLS LG-71-15-0077-15

Dodging the Memory Hole Los Angeles, CA, 2016-10-14

2

Archive-It, a subscription-based service, allows creation of collections

> 3,000 collections

> 340 institutions

> 10B archived pages

3

Collection title

Collection categorization based on the

curator

Seed URI

Metadata about the collection

Text search box

The group that the resource belongs to

List of the seed

URIs

Timespan of the resource

and the number of times it has been captured

4

Collection understanding and collection summarization are not currently supported Not easy to answer “what’s in that collection?” or “how is this collection different from others”?

5

There is more than one collection about “Egyptian Revolution”

• “2010-2011 Arab Spring” https://archive-it.org/collections/3101• “North Africa & the Middle East 2011-2013” https://archive-it.org/collections/2349• “Egypt Revolution and Politics” https://archive-it.org/collections/2358

6

One of at least seven Human Rights collections…

7

8

9

Our early attempts at collection understanding tried to include everything…

“Visualizing digital collections at Archive-It”, JCDL 2012.http://ws-dl.blogspot.com/2012/08/2012-08-10-ms-thesis-visualizing.html

10

1000s of seeds X 1000s of archived pages == Conventional Vis Methods Not Applicable

11

Idea: Storytelling

12

Stories in literature

Story elements: setting, characters, sequence, exposition, conflict, climax, resolution

Once upon a time

http://www.learner.org/interactives/story/

13

Stories in social media“It's hard to define a story, but I know it when I see it” (Alexander, 2008)

basically, just arranging web pages in time

14

“Storytelling” is becoming a popular technique in social media

15

What are the limitations of storytelling services?

16

The Egyptian Revolution on Storify

17

Bookmarking, not preserving!

18

Despite these limitations, how do we combine storytelling & archives?

19

Use interface people already know how to use to summarize collections

Archived collectionsStorytelling services

Archived enriched stories

20

We sample k mementos from N pages of the collection (k << N) to create a summary story

S1

S2

S3

S4

S2

S1

S3

Collection Y

S3

S2

S1

Collection Z

Archive-It Collections

Collection X

Story

The Web

21

Yasmin hand-crafted stories to summarize the Egyptian Revolution collection for her son, Yousof

https://storify.com/yasmina_anwar/the-egyptian-revolution-on-archive-it-collection

https://storify.com/yasmina_anwar/the-story-of-the-egyptian-revolution-from-archive-

22

How do we generate this automatically?

23

Collections have two dimensions:{Fixed, Sliding} X {Page, Time}

t1 t3t2 t5t4 tk

URI

Time

t6

24

Fixed Page, Fixed Time

A desktop Chrome user-agenthttp://www.cnn.com/2014/02/24/world/africa/egypt-politics/index.html?hpt=wo_c2

Android Chrome user-agenthttp://www.cnn.com/2014/02/24/world/africa/egypt-politics/index.html?hpt=wo_c2

Schneider and McCown, “First Steps in Archiving the Mobile Web: Automated Discovery of Mobile Websites”, JCDL 2013.Kelly et al. “A Method for Identifying Personalized Representations in Web Archives”, D-Lib Magazine 2013 .

25

Feb 1 Feb 1 Feb 2

Feb 4 Feb 5 Feb 7

Feb 9 Feb 11 Feb 11

Fixed Page, Sliding Time

26

Feb. 11, 2011Mubarak resigns Sliding Page, Fixed Time

27

Jan 27 Jan 31

Feb 7Feb 4

Feb 11 Feb 11

Feb 2

Jan 25

Feb 10

Sliding Page, Sliding Time

28

The Dark and Stormy Archives (DSA) framework

Establish a baseline

Reduce the candidate pool of archived pages

Select good representative

pages

Characteristics of human-generated

Stories

Characteristics of Archive-It collections

Exclude duplicates

Exclude off-topic pages

Exclude non-English Language

Dynamically slice the collection

Cluster the pages in each slice

Select high-quality pages from each

cluster

Order pages by time

Visualize

https://pbs.twimg.com/media/BQcpj7ACMAAHRp4.jpg

29

Establish a baseline of social media stories

"Characteristics of Social Media Stories”, TPDL 2015, IJDL 2016.

30

What is the length of a story(the number of resources per story)?

This story has 31 resources

1

3

2

31

What are the types of resources that compose a story?

Quotes

Video

This story has • 19 quotes • 8 images• 4 videos

32

What are the most frequently used domains?

Twitter.com

Twitter.com

Twitter.com

This story has • 90% twitter.com• 7% instagram.com• 3% facebook.com

33

Top 25 domains represents 92% of all domains

34

What differentiates a popular story? (popular = stories with the top 25% of views)

19,795 views 64 views

35

The distributions for the features of the stories

• Based on Kruskal-Wallis test, at the p ≤ 0.05 significance level, the popular and the unpopular stories are different in terms of most of the features

• Popular stories tend to have:• more web elements (medians of 28 vs. 21) • longer timespan (5 hours vs. 2 hours) than the unpopular stories

36

Do popular stories have a lower decay rate?

The 75th percentile of decay rate per popular story is 10% of the resources, while it is 15% in the unpopular stories

37

We found that 28 mementos is a good number for the resources in the stories.

38

Establish a baseline of current Archive-It collections

"Characteristics of Social Media Stories. What makes a good story?", International Journal on Digital Libraries 2016.

39

The mean and median number of

URIs in a collection

This collection has 435 seed URIs

40

The mean and median number of mementos per URI

This seed URI has 16 mementos

41

The most frequent used domains

abcnews.go.com

blogspot.com

This collection has 30% abcnews.com, 10% blogspot.com, 3% facebook.com

42

Archive-It top 25 is fundamentally different than Storify top 25

43

Archive-It top 25 is fundamentally different than Storify top 25

Twitter is #10 not #1

44

What we archive and what we share on social mediaare different subsets of the web(seeds != shares)

see also: Brunelle, et al., “The impact of JavaScript on archivability”, IJDL 2015

45

Detecting off-topic pages

"Detecting Off-Topic Pages in Web Archives”, TPDL 2015, IJDL 2016.

46

Archive-It provides their partners with tools that allow them to build themed collections

47

Archive-It tools are about HTTP events / mechanics, not “content”

48

These tools won’t detect that > 60% of mementos of hamdeensabahy.com are off-topic

May 13, 2012: The page started as on-topic.

May 24, 2012: Off-topic due to adatabase error.

Mar. 21, 2013: Not working because offinancial problems.

May 21, 2013: On-topic again June 5, 2014: The site has been hacked Oct. 10, 2014: The domain has expired.

http://wayback.archive-it.org/2358/*/http://hamdeensabahy.com

49

How do we automatically detect off-topic pages?

50

Textual contentcosine similarity, intersection of the most frequent terms, Jaccard similarity

Method Similaritycosine 0.7TF-Intersection 0.6Jaccard 0.5

51

Textual contentcosine similarity, intersection of the most frequent terms, Jaccard similarity

Method Similaritycosine 0.7TF-Intersection 0.6Jaccard 0.5

Method Similaritycosine 0.0TF-Intersection 0.0Jaccard 0.0

52

Semantics of the textWeb based kernel function using the search engine (SE)

Sahami and Heilman, A Web-based Kernel Function for Measuring the Similarity of Short Text Snippets, WWW 2006

53

Semantics of the textWeb based kernel function using the search engine (SE)

Method SimilaritySE-Kernel 0.7

Sahami and Heilman, A Web-based Kernel Function for Measuring the Similarity of Short Text Snippets, WWW 2006

54

Structural methodsno. of words, content-length

100 109

Method % changeWordCount 0.09

55

Structural methodsno. of words, content-length

100 109

100 5

Method % changeWordCount 0.09

Method % changeWordCount -0.95

56

We built a gold standard data set to evaluate the methods

57

We manually labeled 15,760 mementos

Egypt Revolution and PoliticsURI-Rs: 136URI-Ms: 6,886Off-topic URI-Ms: 384

Occupy MovementURI-Rs: 255URI-Ms: 6,570Off-topic URI-Ms: 458

Columbia Univ. Human Rights collectionURI-Rs: 198URI-Ms: 2,304Off-topic URI-Ms: 94

58

Evaluated 6 methods + combos at 21 thresholdsAveraged the results at each threshold over the three gold standard collections

Similarity Measure Threshold FP FN FP+FN ACC F1 AUC

(Cosine,WordCount) (0.10,-0.85) 24 10 34 0.987 0.906 0.968

(Cosine,SEKernel) (0.10,0.00) 6 35 40 0.990 0.901 0.934

Cosine 0.15 31 22 53 0.983 0.881 0.961

(WordCount,SEKernel) (-0.80,0.00) 14 27 42 0.985 0.818 0.885

WordCount -0.85 6 44 50 0.982 0.806 0.870

SEKernel 0.05 64 83 147 0.965 0.683 0.865

Bytes -0.65 28 133 161 0.962 0.584 0.746

Jaccard 0.05 74 86 159 0.962 0.538 0.809

TF-Intersection 0.00 49 104 153 0.967 0.537 0.740

59

Average precision of 0.89 on 18 different Archive-It collections

(Cosine,WordCount) with (0.10,-0.85) thresholds

60

How do we dynamically divide the collections into appropriate slices?(in other words, how do we pick just 28?)

61

We expected most collections to look like this…

The Global Food Crisis collection at Archive-It

62

This is what we found

Egypt Revolution and Politics

Human Rights April 16 Archive Virginia Tech Shooting

Jasmine Revolution 2011 Wikileaks Document Release

63

Selecting representative pages for generating stories(skipping clustering details, but goal is k=28)

64

Quality metrics for selecting mementos• In the DSA, memento quality Mq is calculated as

following: Mq = (1 − wm*Dm) + wql*Sql + wqc*Sqc

• Dm is the memento damage (Brunelle, JCDL 2014)

• Sql is the snippet quality based on the URI level• Sqc is the snippet quality based on URI category• wm, wql, wqc are the weights of memento damage, level,

and category

65

We prefer a higher quality memento (Dm)

http://wayback.archive-it.org/2358/20110201231457/http://news.blogs.cnn.com/category/world/egypt-world-latest-news/

http://wayback.archive-it.org/2358/20110201231622/http://www.bbc.co.uk/news/world/middle_east/

Brunelle et al. Not All Mementos Are Created Equal: Measuring The Impact Of Missing Resources, JCDL 2014

66

We prefer pages with attractive snippets

https://wayback.archive-it.org/2358/20110207193404/http://news.blogs.cnn.com/2011/02/07/egypt-crisis-country-to-auction-treasury-bills/

https://wayback.archive-it.org/2358/20110207194425/http://www.cnn.com/2011/WORLD/africa/02/07/egypt.google.executive/index.html?hpt=T1

67

We prefer deep links over high level domains (Sql)

Feb. 11, 2011: the homepage of BBC on Storify

Feb. 11, 2011: the homepage of BBC Middle East section on Storify

Feb. 11, 2011: the article of BBC on Storify

https://wayback.archive-it.org/2358/20110211191429/http://www.bbc.co.uk/

https://wayback.archive-it.org/2358/20110211192204/http://www.bbc.co.uk/news/world-middle-east-12433045

https://wayback.archive-it.org/2358/20110211191942/http://www.bbc.co.uk/news/world/middle_east/

68

Social media pages may not produce good snippets (Sqc)

http://wayback.archive-it.org/1784/20100131023240/http:/twitter.com/Haitifeed/http://wayback.archive-it.org/2358/20141225080305/https:/www.facebook.com/elshaheeed.co.uk

69

Visualizing stories in Storify

70

Remember Yasmin’s hand-crafted stories?

71

Remember Yasmin’s hand-crafted stories?

72

We extract the metadata of the pages and order them chronologically

{ "elements":[ { "permalink":"http://wayback.archive-it.org/694/20070523182134/http://www.usatoday.com/news/nation/2007-04-16-virginia-tech_N.htm", "type":"link", "source":{"href":"http://www.usatoday.com", "name":"www.usatoday.com @ 23, May 2007"} }, { "permalink":"http://wayback.archive-it.org/694/20070530182159/http://www.time.com/time/specials/2007/vatech_victims", "type":"link", "source":{"href":"http://www.time.com", "name":"www.time.com @ 30, May 2007" } }, { "permalink":"http://wayback.archive-it.org/694/20070530182206/http://www.collegiatetimes.com/", "type":"link", "source":{"href":"http://www.collegiatetimes.com", "name":"www.collegiatetimes.com @ 30, May 2007" } }, { "permalink":"http://wayback.archive-it.org/694/20070606234248/http://hokies416.wordpress.com/", "type":"link", "source":{ "href":"http://hokies416.wordpress.com", "name":"hokies416.wordpress.com @ 06, Jun 2007" } }, …{ "permalink":"http://wayback.archive-it.org/694/20070620234329/http://www.hokiesports.com/april16/", "type":"link", "source":{"href":"http://www.hokiesports.com", "name":"www.hokiesports.com @ 20, Jun 2007" } }, ],

"description":"This is an automatically generated story from Archive-It collection.", "title":"April 16 Archive ”}

Using the Storify API, we override the default metadata to generate more attractive snippets

73

Example of an automatically generated story

Notice the good metadata: images, titles with dates, favicons

74

Evaluating the Dark and Stormy Archive framework(how good are the automatically generated stories?)

75

Evaluation is tricky!(two perfectly good stories could have non-overlapping k=28 elements!)

• We use human evaluators (via Amazon's Mechanical Turk) to compare:

• Human-generated stories• DSA (automatically) generated stories• Randomly generated stories

• Successful evaluation means:• Human and DSA stories are indistinguishable• Human and DSA stories are better than Random

76

Our guidelines for expert archivists at Archive-It for generating stories from the collections

77

We received 23 stories for 10 Archive-It collections

SPST is “Sliding Page, Sliding Time”SPFT is “Sliding Page, Fixed Time” FPST is “Fixed Page, Sliding Time”

78https://storify.com/mturk_exp/3649b1s-57218803f5db94d11030f90b

• Generated by domain experts• Sliding Page, Sliding Time• The Boston Marathon

Bombing collection

79

Automatically generated stories from archived collections

1. Obtain the seed list and the TimeMap of URIs from the front-end interface of Archive- It

2. Extract the HTML of the mementos from the WARC files (locally hosted at ODU) and download the collections that we do not have in the ODU mirror from Archive-It

3. Extract the text of the page using the Boilerpipe library 4. Eliminate the off-topic pages based on the best-performing method ((Cosine,

Word-Count) with the suggested thresholds (0.1, −0.85))5. Exclude duplicates in each TimeMap 6. Eliminate the non-English language pages7. Slice the collection dynamically and then cluster the mementos of each slice

using DBSCAN algorithm8. Apply the quality metrics to select the best representative pages9. Sort the selected mementos chronologically then put them and their metadata

in a JSON object

80https://storify.com/mturk_exp/3649b0s

• Automatically generated story • Sliding Page, Sliding Time• The Boston Marathon

Bombing collection

81

Random stories

28 mementos were randomly selected from each collection before excluding off-topic and duplicate pages

82https://storify.com/mturk_exp/3649b2s-57227227bb79 048c2d0388dc

• Randomly generated story• Sliding Page, Sliding Time• The Boston Marathon

Bombing collection

83https://storify.com/mturk_exp/3649bads

if someone prefers this story, we exclude their results

• Poorly generated story• The same memento, 28 times• The Boston Marathon

Bombing collection

84

MT experiment setup

• Three HITs for each story (69 HITs to evaluate 23 stories); two comparisons per HIT:

• HIT1: human vs. automatic, human vs. poor• HIT2: human vs. random, human vs. poor• HIT3: random vs. automatic, automatic vs. poor

• 15 distinct turkers with master qualification (i.e., high acceptance rate) for each HIT

• We rejected the submissions contained poorly-generated stories and the HITs that were completed in less than 10 seconds (mean time per HIT = 7 minutes)

• 989 out of 1,035 (69*15) valid HITs

• We awarded the turker $0.50 per HIT

https://www.mturk.com/mturk/help?helpPage=worker#what_is_master_worker

85

A sample HIT

86

DSA == Human(Human,DSA) > Random

87

Automatic versus Human

Sliding Page, Sliding Time Sliding Page, Fixed Time Fixed Page, Sliding Time

88

Human versus Random

Sliding Page, Sliding Time Sliding Page, Fixed Time Fixed Page, Sliding Time

89

Automatic versus Random

Sliding Page, Sliding Time Sliding Page, Fixed Time Fixed Page, Sliding Time

90

Success!

DSA-generated stories are just as good as stories generated by human experts

91

Use interface people already know how to use to summarize collections

Archived collectionsStorytelling services

Archived enriched stories

All the code, datasets, papers, slides, etc.:http://bit.ly/YasminPhD

top related