Re-Inventing Journalistic Sourcing? Dr Neil Thurman @neilthurman - - PowerPoint PPT Presentation

▶
re inventing journalistic
SMART_READER_LITE
LIVE PREVIEW

Re-Inventing Journalistic Sourcing? Dr Neil Thurman @neilthurman - - PowerPoint PPT Presentation

May 30, 2023 143 likes •889 views

A Digital Nose For News : Re-Inventing Journalistic Sourcing? Dr Neil Thurman @neilthurman n.j.thurman@city.ac.uk Probability of Computerisation We dont think it is desirable that journalism is done with algorithms Email to

slide-1
SLIDE 1

A Digital Nose For News: Re-Inventing Journalistic Sourcing?

Dr Neil Thurman @neilthurman n.j.thurman@city.ac.uk

slide-2
SLIDE 2
slide-3
SLIDE 3
slide-4
SLIDE 4

Probability of Computerisation

slide-5
SLIDE 5
slide-6
SLIDE 6

‘We don’t think it is … desirable that journalism is done with algorithms’ Email to Konstantin Dörr

slide-7
SLIDE 7
slide-8
SLIDE 8
slide-9
SLIDE 9
  • Social and professional contexts
  • How they work.
  • Biases?
  • Changes in journalistic work and
  • utputs

Tools for computational news detection & verification

slide-10
SLIDE 10

SocialSensor is a single tool that quickly surfaces trusted news stories from social media – with context.

 A Single Tool: one platform, one interface  Quickly: in real time  Surfaces: automatically discovers and clusters  Trusted: automatic support in verification process  Material: any material (text, image, audio, video = multimedia)  Social Media: across relevant social media platforms  With Context: location, time, sentiment, influence

slide-11
SLIDE 11
slide-12
SLIDE 12
slide-13
SLIDE 13
slide-14
SLIDE 14
slide-15
SLIDE 15
slide-16
SLIDE 16
  • 1. To what extent does social media

break news first, and how much news does it carry that’s not covered elsewhere?

  • 2. And, in addition to ‘surfacing’ news,

what else can tools like Social Sensor do?

slide-17
SLIDE 17

Source: Osborn, M. and Dredze, M (2014) Facebook, Twitter and Google Plus for Breaking News: Is there a winner? Proceedings of the Eight International AAAI Conference on Weblogs and Social Media.

etc

Broke 1st or 1st=

slide-18
SLIDE 18

Where Twitter was first

Source: Petrovic, S. Osborne, M, et al, 2013 Can Twitter Replace Newswire for Breaking News? Proceedings of the Seventh International AAAI Conference on Weblogs and Social Media

slide-19
SLIDE 19

Source: Petrovic, S. Osborne, M, et al, 2013 Can Twitter Replace Newswire for Breaking News? Proceedings of the Seventh International AAAI Conference on Weblogs and Social Media

Only carried on Twitter

Death of Canadian Ice Hockey player

slide-20
SLIDE 20

Source: Petrovic, S. Osborne, M, et al, 2013 Can Twitter Replace Newswire for Breaking News? Proceedings of the Seventh International AAAI Conference on Weblogs and Social Media

Only carried on Twitter

Identification of looter’s car, London riots 2011

slide-21
SLIDE 21

1 2 3 4 8 UK & Dutch Quality & Tabloid Newspapers (2011) 7 Elite US newspapers and TV stations (2010-11) 2 quality Flemish newspapers (2013)

Newspaper articles / Broadcast news packages quoting social media (per outlet per day)

Source: Broersma and Graham (2013) Source: Paulussen and Harder (2014) Source: Soo Jung Moon and Patrick Hadley (2014)
slide-22
SLIDE 22
  • Providing editors with information on

trends in popularity and sentiment

  • Alerting newsrooms to ongoing

developments in running stories and providing contacts and content

  • Giving journalists information on the

reliability of contributors and the veracity of content

slide-23
SLIDE 23

Source: Broersma and Graham (2013)

slide-24
SLIDE 24

5 10 15 20 25 30 35 40

Source: Broersma and Graham (2013)

Types of story using Tweets as source (%)

slide-25
SLIDE 25

Types of social media contributor quoted in UK & Dutch newspapers

Source: Broersma and Graham (2013)

slide-26
SLIDE 26

Types of social media contributor quoted in UK & Dutch newspapers

Source: Broersma and Graham (2013)

slide-27
SLIDE 27

“the biggest problem is how to exploit the vast amount of content in social media with a small team” – MSN journalist (pers. Comm.) “we need algorithms to take more onus off human being, to pick and understand the best elements” – New York Times’ Social Media Team member (pers. Comm.) “Current tools aren’t powerful enough” – CNN social media expert (pers. Comm.)

slide-28
SLIDE 28
  • J’aime pas Bieber, 1D le rap et plein d’autres
  • conneries. Vous pouvez m’amener 500 haters

je changerai pas d’avis.

  • This wine is going down a lil to smoothly. Here

comes trouble.

  • LIMA HARI BULAN LIMA ! KEK SEBESAR

GUNUNG ! kena belajar buat

  • kek ni, tinggal 2 bulan jea lagi -.-’
  • RT ZorianRamone: Happy Bday

Less than 5% of Tweets carry newsrelated content

Representative non-events:

  • Running traditional First Story Detection

systems on Twitter produces a mass of false positives

  • Less than 1% of events detected in

Twitter are news related

Event detection in Twitter

Source: Osborne & Benjamin Van Durme in Callison- Burch

slide-29
SLIDE 29

Examples of false positives

Source: Osborne & Benjamin Van Durme in Callison-Burch

  • Juicy Couture, Ed Hardy, Coach, Kate Spade and many

more! Stay tuned for more brands coming in http://. . .

  • i lovee my nephew hair :D
  • Going to look at houses tomorrow. One of them

is & right behind Sonic Taco Casa. If I live there, I might weigh 400 lbs within a year.

  • Hope a bad morning doesnt turn into a bad day...
slide-30
SLIDE 30
slide-31
SLIDE 31

Lyse Doucet, Chief International Correspondent: @BBCLyseDoucet Gavin Hewitt, Europe Editor: @BBCGavinHewitt Lucy Williamson, Paris Correspondent: @LucyWilliamson Fergal Keane, World Affairs Correspondent: @FergalKeane47 Chris Morris, Correspondent: @BBCChrisMorris Christian Fraser, Correspondent: @ChristianFraser Damian Grammaticas, Correspondent: @DNGBBC Simon Wilson, Europe Bureau Editor: @Siwilso Piers Schofield, Senior Europe Producer: @Inglesi Natalie Morton, Senior Producer: @NatalieMortonTV Imelda Flattery, Senior Producer: @ImeldaFlattery Frank Gardner, Security Correspondent: @FrankRGardner Gordon Corera, Security Correspondent: @GordonCorera

Example list used to ‘seed’ News Hound database

slide-32
SLIDE 32
slide-33
SLIDE 33

Criteria Score On ‘seed’ list? 150 Each seed that follows them 5 Each seed they follow 2 Send at least 10 tweets per day 50 Verified with Twitter’s blue tick 25 Presence on at least 50 Twitter lists 25

Scoring newshounds

slide-34
SLIDE 34
slide-35
SLIDE 35

Dispersion of news on social media

slide-36
SLIDE 36

52

23

10 20 30 40 50 60

Males Female Institutional Accounts

Who are the ‘news hounds’?

slide-37
SLIDE 37

Who are the ‘news hounds’?

slide-38
SLIDE 38

News hounds scoring system

Criteria Score On ‘seed’ list? 150 Each seed that follows them 5 Each seed they follow 2 Send at least 10 tweets per day 50 Verified with Twitter’s blue tick 25 Presence on at least 50 Twitter lists 25

slide-39
SLIDE 39

Computational journalism tools

Tuned to: Most mentioned, Most followed & Most Vocal…?or

Agents for change?

slide-40
SLIDE 40

Research Potential

slide-41
SLIDE 41

The Personal Brand

slide-42
SLIDE 42

The Personal Brand

#6924 #6758 @Le_Figaro @wblau

slide-43
SLIDE 43

#43

slide-44
SLIDE 44

Burstiness

slide-45
SLIDE 45
slide-46
SLIDE 46
slide-47
SLIDE 47
slide-48
SLIDE 48

Tony Harcup & Deirdre O'Neill, 2010

News values

slide-49
SLIDE 49
  • ....political, structural and natural root

causes and contexts

  • the accounts of the people involved

rather than third interpretations by a third party….

Source: NGO-EC Liaison Committee, 1989

Alternative News Values?

slide-50
SLIDE 50

Verification

slide-51
SLIDE 51
slide-52
SLIDE 52
slide-53
SLIDE 53
slide-54
SLIDE 54
slide-55
SLIDE 55
slide-56
SLIDE 56
slide-57
SLIDE 57
  • Content
  • Contributor
  • Context

Principles for social media verification

slide-58
SLIDE 58

Content

slide-59
SLIDE 59

Contributor

slide-60
SLIDE 60

Context

slide-61
SLIDE 61

500 1000 1500 2000 2500 3000 3500

Bostom Marathon Bombings 2013 US tornadoes 2010 Tweets per min

slide-62
SLIDE 62
slide-63
SLIDE 63

If training= And test=

slide-64
SLIDE 64
slide-65
SLIDE 65
  • No. of Tweets

HISTORY Frequency HISTORY

  • No. of followers

POPULARITY

  • No. of follows

POPULARITY Retweets INFLUENCE

Computing Contributor Credibility

slide-66
SLIDE 66

Grade 0-9 Standard Deviation Journalists’ Evaluation 5.67 2.10 Truthmeter Evaluation 5.71 2.45 Human vs. algorithmic evaluation of social media contributors

slide-67
SLIDE 67

Inactive! Yeah, but check out his followers!

slide-68
SLIDE 68

Weight

  • No. of Tweets

HISTORY 1 Frequency HISTORY 2

5/10 What? She’s Deputy Leader of the Labour Party!

slide-69
SLIDE 69
  • The social and professional contexts
  • How they work
  • Biases?
  • Agents of change?

Digital ‘Nose for News’

slide-70
SLIDE 70
  • Rely on journalistic input
  • Success measured against

journalistic ‘ground truth’

  • Created in our own image

Digital ‘Nose for News’

slide-71
SLIDE 71
  • Its biases are ours:

–short-termism –‘Personalization’ – Demography

Digital ‘Nose for News’

slide-72
SLIDE 72

“To enjoy the privilege

  • f making stockings for

everyone is too important to grant to any individual”

slide-73
SLIDE 73

Thank you!

Dr Neil Thurman @neilthurman n.j.thurman@city.ac.uk