Top Banner
The Geography of Online News Engagement Martin Saveski, MIT Media Lab, Cambridge, USA Daniele Quercia, Yahoo Labs, Barcelona, Spain Amin Mantrach, Yahoo Labs, Barcelona, Spain
18

The Geography of Online News Engagement Martin Saveski, MIT Media Lab, Cambridge, USA Daniele Quercia, Yahoo Labs, Barcelona, Spain Amin Mantrach, Yahoo.

Dec 24, 2015

Download

Documents

Amy Mcgee
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: The Geography of Online News Engagement Martin Saveski, MIT Media Lab, Cambridge, USA Daniele Quercia, Yahoo Labs, Barcelona, Spain Amin Mantrach, Yahoo.

T h e G e o g r a p h y o f O n l i n e N e w s E n g a g e m e n t

M a r t i n S a v e s k i , M I T M e d i a L a b , C a m b r i d g e , U S A

D a n i e l e Q u e r c i a , Ya h o o L a b s , B a r c e l o n a , S p a i n

A m i n M a n t r a c h , Ya h o o L a b s , B a r c e l o n a , S p a i n

Page 2: The Geography of Online News Engagement Martin Saveski, MIT Media Lab, Cambridge, USA Daniele Quercia, Yahoo Labs, Barcelona, Spain Amin Mantrach, Yahoo.

2

Outline

Motivations; Contributions; Data description; Does time zone affect user engagement in online news platforms? Can the gravity model alone predict user engagement? How does user engagement correlates with the big five personality

traits? How does user engagement correlates with the socio economic factors? Putting all factors together for a better understanding of user

engagement.

Page 3: The Geography of Online News Engagement Martin Saveski, MIT Media Lab, Cambridge, USA Daniele Quercia, Yahoo Labs, Barcelona, Spain Amin Mantrach, Yahoo.

3

Motivations

Despite its importance, the geographic processes of online engagement

on news platforms have not been widely studied;

Yahoo News site for more than two years: articles and user comments

Page 4: The Geography of Online News Engagement Martin Saveski, MIT Media Lab, Cambridge, USA Daniele Quercia, Yahoo Labs, Barcelona, Spain Amin Mantrach, Yahoo.

4

Contributions

In Online news platforms,

Users engage with each other depending on where they live

Page 5: The Geography of Online News Engagement Martin Saveski, MIT Media Lab, Cambridge, USA Daniele Quercia, Yahoo Labs, Barcelona, Spain Amin Mantrach, Yahoo.

5

Contributions: Socio economic factors and user engagement

Users in states with:

high levels of education and well-being comment articles about research & technology, but not politics, gossip or sport;

high levels of crime and unemployment comment on articles about sports, but not those about economy or research and technology;

Page 6: The Geography of Online News Engagement Martin Saveski, MIT Media Lab, Cambridge, USA Daniele Quercia, Yahoo Labs, Barcelona, Spain Amin Mantrach, Yahoo.

6

Contributions: Personality Traits and user engagement:

Users from

states low in neuroticism (emotionally stable) comment on articles about music ;

open and extravert states comment on articles about sport;

conscientious states on articles about economics.

Page 7: The Geography of Online News Engagement Martin Saveski, MIT Media Lab, Cambridge, USA Daniele Quercia, Yahoo Labs, Barcelona, Spain Amin Mantrach, Yahoo.

7

Related work

Influence of time on our actions online:› “emotion words by Twitter users influenced by times

zones”

News in tweets and geographics spread on Twitter:› “Reciprocal relations between people users who live no

more than 3 times zones away”› Physical distance constrained the spread of hashtags

Page 8: The Geography of Online News Engagement Martin Saveski, MIT Media Lab, Cambridge, USA Daniele Quercia, Yahoo Labs, Barcelona, Spain Amin Mantrach, Yahoo.

8

Data description

Random sample of 200K news articles and 41M associated comments;

Published from August 2010 to February 2013; On Yahoo! News US; English articles; Sources: Reuters, ABC News, AP, etc.; From anonymous user we have IP address state(Yahoo places Web

service).

Page 9: The Geography of Online News Engagement Martin Saveski, MIT Media Lab, Cambridge, USA Daniele Quercia, Yahoo Labs, Barcelona, Spain Amin Mantrach, Yahoo.

9

State commenting graph

Nodes: US states Egde weight: number of times two users in state i and j comment on the

same article

Page 10: The Geography of Online News Engagement Martin Saveski, MIT Media Lab, Cambridge, USA Daniele Quercia, Yahoo Labs, Barcelona, Spain Amin Mantrach, Yahoo.

10

The time zone effect

Users in the same TZ preferentially engage with the same articles, while users in different time zones engage with different articles

Engagement in k-time zone apart: count the number of times users from k-time zone apart engage in the same articles;

Null model: We shuffle user’s time zone assignment

Page 11: The Geography of Online News Engagement Martin Saveski, MIT Media Lab, Cambridge, USA Daniele Quercia, Yahoo Labs, Barcelona, Spain Amin Mantrach, Yahoo.

11

The Geography of News Engagement

The gravity model

F measures the estimated engagement between two states g is a scaling constant; di,j is the euclian distance between two states centers; mk is number of users of state k.

F correlates with number of the observed number of comments with a pearson correlation of 0.70

Page 12: The Geography of Online News Engagement Martin Saveski, MIT Media Lab, Cambridge, USA Daniele Quercia, Yahoo Labs, Barcelona, Spain Amin Mantrach, Yahoo.

12

Assigning topic distributions to states

13.8% of articles are editorially labeled with IPTC categories IPTC consists of 1400 topics organized in a taxonomy; Average category per articles is 5; By using user engagement (on comments) we aggregated articles

topics to form states topics:› Each time a user from state comment on an article, the tags contribute to the state

topical distribution;› Tags contribution is normalized by the number of times they are used (to discount

popular tags, similar to idf to discount stop words).

Page 13: The Geography of Online News Engagement Martin Saveski, MIT Media Lab, Cambridge, USA Daniele Quercia, Yahoo Labs, Barcelona, Spain Amin Mantrach, Yahoo.

13

The Big Five Personnality Traits

1. Openess: Imaginative, spontaneous, and adventurous individuals;

2. Conscientiousness: Ambitious, resourceful and persistent individuals;

3. Extraversion: Individuals who are sociable and tend to seek excite- ment;

4. Agreeableness: are trusting, altruistic, tender-minded, and are motivated to maintain positive relationships with others

5. Neuroticism: Finally, emotionally liable and impulsive individuals.

These factors have been also studied at the state level (strongly correlated with socio-economic indicators) [Rentfrow et al.]

Page 14: The Geography of Online News Engagement Martin Saveski, MIT Media Lab, Cambridge, USA Daniele Quercia, Yahoo Labs, Barcelona, Spain Amin Mantrach, Yahoo.

14

Correlation of news user engagement factors with state personality scores

Page 15: The Geography of Online News Engagement Martin Saveski, MIT Media Lab, Cambridge, USA Daniele Quercia, Yahoo Labs, Barcelona, Spain Amin Mantrach, Yahoo.

15

Socioeconomic Indicators

1. Well-being index; 2. Crime level 3. Rate of unemployment; 4. Gross State Product; 5. Education level.

Page 16: The Geography of Online News Engagement Martin Saveski, MIT Media Lab, Cambridge, USA Daniele Quercia, Yahoo Labs, Barcelona, Spain Amin Mantrach, Yahoo.

16

Correlation of news user engagement factors with socio economic indicators

Page 17: The Geography of Online News Engagement Martin Saveski, MIT Media Lab, Cambridge, USA Daniele Quercia, Yahoo Labs, Barcelona, Spain Amin Mantrach, Yahoo.

17

Conclusions: Putting all together

Page 18: The Geography of Online News Engagement Martin Saveski, MIT Media Lab, Cambridge, USA Daniele Quercia, Yahoo Labs, Barcelona, Spain Amin Mantrach, Yahoo.

Questions

18