Finding News Curators in Twitter
9 likes5,114 views
The document discusses research into identifying "news story curators" on Twitter - users who share and discuss news articles in a way that provides additional context and information about the news topic. The researchers analyzed how users interacted with news articles from the BBC and Al Jazeera, labeling users as topic-focused or not and human or automated. Machine learning models were able to accurately identify news story curators based on user profile features like followers, tweets, and topic focus. These curators were found to provide more relevant information about news stories than users with the most followers or most shared stories. Future work could explore how to better identify interesting and serendipitous curators.
![Example
Al Jazeera English news article about the civil war in Syria
“Syria allows UN to step up food aid” [16 Jan 2013]
Users that posted the article in Twitter
Whom would you follow to find out more about the civil war in Syria?
4
#Followers Is tweeting about
@RevolutionSyria 88,122 Syria
@KenanFreeSyria 13,388 Syria
@UP_food 703 Food
@KeriJSmith 8,838 Breaking news/top stories
@BreakingNews 5,662,866 Breaking news/top stories](https://image.slidesharecdn.com/snow2013-2-130512151110-phpapp02/85/Finding-News-Curators-in-Twitter-4-320.jpg)
![Data sets
Step 1: Selection of news articles
¨ News articles published in early 2013 from
¤ BBC World Service [BBC] 75 articles
¤ Al Jazeera English [AJE] 155 articles
¨ Stories: Obama's inauguration, Mali conflict, Pollution in Beijing, etc.
Step 2 : News crowd detection
¨ All users who tweeted the article within the first 6 hours after
publication
Step 3: User characteristics
¨ Extraction of data from each user in the news crowd (e.g. further
tweets, profile information)
7](https://image.slidesharecdn.com/snow2013-2-130512151110-phpapp02/85/Finding-News-Curators-in-Twitter-7-320.jpg)
![Simple models
UserIsHuman
UserFracURL >= 0.85
automatic,
otherwise human
Model
Human class:
Prec/Rec: 0.85
AUC: 0.81
Evaluation
UserIsInterestedInStory
UserSectionsQ >= 0.9
not-interested,
otherwise interested
Model
Interested class:
Prec: 0.48 / Rec: 0.93
AUC: 0.83
Evaluation
Preselection
The user must have
• At least 1,000 followers
• Posted an article that is estimated related to the original article [1]
13
[1] J. Lehmann, C. Castillo, M. Lalmas, and E. Zuckerman. Transient news crowds in social media. In ICWSM, 2013.
feature (one) selection + random forest algorithm](https://image.slidesharecdn.com/snow2013-2-130512151110-phpapp02/85/Finding-News-Curators-in-Twitter-13-320.jpg)
![Precision-oriented evaluation
We compared our method with two baseline approaches
¨ Users with the largest number of followers [FOLLOWER-APPROACH]
¨ Users with the largest number of stories detected as related to the original one [STORY-APPROACH]
Data
¨ Sample of 20 news articles that had at least one curator, detected using the complex model
with a confidence value >= 0.75
¨ We extracted for each article the same number of possible curators using the other two
approaches
¨ We asked three assessors to evaluate the results
(question Q1 – UserIsInterestedInStory)
¨ About 210 labels for 70 units were collected
Results
true positive/false positive
FOLLOWER-APPROACH: 2/18 = 11%
STORY-APPROACH: 5/20 = 25%
OUR APPROACH: 6/16 = 38%
15](https://image.slidesharecdn.com/snow2013-2-130512151110-phpapp02/85/Finding-News-Curators-in-Twitter-15-320.jpg)
Finding News Curators in Twitter
- 1. Janette Lehmann, Carlos Castillo, Mounia Lalmas, Ethan Zuckerman Finding News Curators in Twitter
- 2. Outline ¨ Motivation ¨ Types of curators ¨ Labeling news story curators ¨ Automatically finding news story curators ¨ Conclusion and future work 2 Photo credit (first slide): Hobvias Sudoneighm (CC-BY).
- 3. Motivation ¨ Twitter has become a powerful tool for the aggregation and consumption of time- sensitive content in general and news in particular. ¨ Journalists use online social media platforms (Twitter, Facebook and others) and blogs to elicit other story angles or verify stories they are working on. To what extend the community of engaged readers - those who share news articles in social media – can contribute to the journalistic process? What kind of roles people play when sharing news? We want to detect users that provide further relevant information to a news story. We call them news story curators. 3
- 4. Example Al Jazeera English news article about the civil war in Syria “Syria allows UN to step up food aid” [16 Jan 2013] Users that posted the article in Twitter Whom would you follow to find out more about the civil war in Syria? 4 #Followers Is tweeting about @RevolutionSyria 88,122 Syria @KenanFreeSyria 13,388 Syria @UP_food 703 Food @KeriJSmith 8,838 Breaking news/top stories @BreakingNews 5,662,866 Breaking news/top stories
- 5. Types of news story curators Human Automatic Topic- unfocused Topic-unfocused curator Disseminating news articles about diverse topics, usually breaking news/top stories à @KeriJSmith News aggregators Collecting news articles (e.g. from RSS feeds) and automatically post their corresponding headlines and URLs à @BreakingNews Topic- focused Topic-focused curator Collecting interesting information with a specific focus, usually a geographic region or a topic à @KenanFreeSyria Topic-focused aggregators Disseminating automatically news with topical focus à @UP_food, @RevolutionSyria 5
- 6. Types of news story curators Human Automatic Topic- unfocused Topic- focused Topic-focused curator Collecting interesting information with a specific focus, usually a geographic region or a topic à @KenanFreeSyria Topic-focused aggregators Disseminating automatically news with topical focus à @UP_food, @RevolutionSyria Valuable curators for a specific story These curators are probably less or not valuable 6
- 7. Data sets Step 1: Selection of news articles ¨ News articles published in early 2013 from ¤ BBC World Service [BBC] 75 articles ¤ Al Jazeera English [AJE] 155 articles ¨ Stories: Obama's inauguration, Mali conflict, Pollution in Beijing, etc. Step 2 : News crowd detection ¨ All users who tweeted the article within the first 6 hours after publication Step 3: User characteristics ¨ Extraction of data from each user in the news crowd (e.g. further tweets, profile information) 7
- 9. Labeling tasks Data ¨ Sample of 20 news articles ¨ For each news article, a sample of 10 users who posted the article ¨ We shown to three assessors: ¤ The title of the news article and a sample of tweets of the user ¤ Profile description and the number of followers of the user Labeling-Questions 9 Q1) Please indicate whether the user is interested or an expert of the topic of the article story: Yes: Most of her/his tweets relate to the topic of the story (e.g. the article is about the conflict in Syria, she/he is often tweeting about the conflict in Syria). Maybe: Many of her/his tweets relate to the topic of the story or she/he is interested in a related topic (e.g. the article is about the conflict in Syria, she/he is tweeting about armed conflicts or the Arabic world). No: She/he is not tweeting about the topic of the story. Unknown: Based on the information of the user it was not possible to label her/him. Q2) Please indicate whether the user is a human or generates tweets automatically: Human: The user has conversations and personal comments in his or her tweets. The text of tweets that have URLs (e.g. to news articles) seems self-written and contain user own opinions. Maybe automatic: The Twitter user has characteristics of an automatic profile, but she/he could be human as well. Automatic: The tweet stream of the user looks automatically generated. The tweets contain only headlines and URLs of news articles. Unknown: Based on the information of the user it was not possible to label her/him as human or automatic.
- 10. Resulting training set Interested? (topic-focused) Human or Automatic? Interested + human n yes no n human automatic AJE 63 21% 79% 71 55% 45% 13% BBC 58 3% 54% 54 35% 65% 1.8% many users are topic-unfocused and automatic 10 We considered only users for which at least two annotators provided a decisive label (Yes or No, Human or Automatic)
- 12. Features Visibility • Number of followers • Number of Twitter lists with user Tweeting activity • Number of tweets per day • Fraction of tweets that contains a re-tweet mark "RT", a URL, a user mention or a hashtag Topic focus • Number of crowds the user belongs to • Number of distinct article sections of the crowds (e.g. sports, business) the user belongs to 12
- 13. Simple models UserIsHuman UserFracURL >= 0.85 automatic, otherwise human Model Human class: Prec/Rec: 0.85 AUC: 0.81 Evaluation UserIsInterestedInStory UserSectionsQ >= 0.9 not-interested, otherwise interested Model Interested class: Prec: 0.48 / Rec: 0.93 AUC: 0.83 Evaluation Preselection The user must have • At least 1,000 followers • Posted an article that is estimated related to the original article [1] 13 [1] J. Lehmann, C. Castillo, M. Lalmas, and E. Zuckerman. Transient news crowds in social media. In ICWSM, 2013. feature (one) selection + random forest algorithm
- 14. Complex models Precision Recall AUC Automatic 0.88 0.84 0.93 Human 0.82 0.86 0.93 Interested 0.95 0.92 0.90 Not-interested 0.53 0.67 0.90 random forest with information-gain-based feature selection random forest with asymmetric misclassification costs false negatives (classifying an interested user as not interested) were considered 5 times more costly than false positives 14
- 15. Precision-oriented evaluation We compared our method with two baseline approaches ¨ Users with the largest number of followers [FOLLOWER-APPROACH] ¨ Users with the largest number of stories detected as related to the original one [STORY-APPROACH] Data ¨ Sample of 20 news articles that had at least one curator, detected using the complex model with a confidence value >= 0.75 ¨ We extracted for each article the same number of possible curators using the other two approaches ¨ We asked three assessors to evaluate the results (question Q1 – UserIsInterestedInStory) ¨ About 210 labels for 70 units were collected Results true positive/false positive FOLLOWER-APPROACH: 2/18 = 11% STORY-APPROACH: 5/20 = 25% OUR APPROACH: 6/16 = 38% 15
- 16. Conclusion and future work We were able to detect and model news story curators, who (could and maybe are) play an important role in the news ecosystem; not only for news readers, but for journalists and editors. ¨ A large amount of activity on Twitter is automatic and some of these news aggregators can be considered to be good curators ¨ Mostly the attention of the user is quickly shifting away - posting a link does not have to reflect a long-standing interest on the subject of the link Future work ¨ Adding other (Twitter) variables to the system that capture, for instance, interestingness and serendipity ¨ Application on other news providers ¨ Analysis of the functionality of popular news aggregators, which are comparable to RSS feeds 16
- 17. Questions and Discussion… 17 Janette Lehmann Universitat Pompeu Fabra jnt.lehmann@gmail.com Carlos Castillo Qatar Computing Research Institute chato@acm.org Mounia Lalmas Yahoo! Labs mounia@acm.org Ethan Zuckerman MIT Center for Civic Media ethanz@media.mit.edu Photocredit:WayneLarge(CC-BY-ND). Photo credits: Hobvias Sudoneighm (CC BY), Thomas Leuthard (CC BY), Mads Iversen (CC BY-NC-SA), Wayne Large (CC BY-ND)