Evaluating Microblog Content Value Paul André paulesque Michael Bernstein Kurt Luther Carnegie Mellon amp Uni Southampton MIT CSAIL Georgia Institute of Technology What content is valued and why ID: 627787
Download Presentation The PPT/PDF document "W HO G IVES A T WEET ?" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
W
HO GIVES A TWEET?Evaluating Microblog Content Value
Paul André
@paulesque Michael BernsteinKurt Luther
Carnegie Mellon &
Uni. Southampton
MIT CSAIL
Georgia Institute of TechnologySlide2Slide3Slide4Slide5Slide6Slide7
?Slide8
?
What content is valued, and why?Slide9
?
What content is valued, and why?
1.
design implications
2.
emerging norms and practiceSlide10
DESIGN
Who Gives a Tweet?anonymous feedback from followers and strangers(analysis of follower ratings only)Slide11
DESIGN
anticipated reciprocityWho Gives a Tweet?anonymous feedback from followers and strangersrate tweets
(provide us data)
receive value in return(ratings from followers)Slide12
DESIGN
wgat_user
:
username:Slide13
RECRUITMENTSlide14
RECRUITMENTSlide15
RECRUITMENTSlide16
1,443 users
rated 43,738 tweetsfrom 21,014 Twitter accountsSlide17
entire dataset
RESULTS36% Worth Reading39% Neutral25%
Not Worth Reading41% Worth Reading
average user Slide18
What content is valued,
and why?Slide19
What content is valued,
and why?1. categories2. reasons whySlide20
What content is valued,
and why?4,220 tweetsGround truth + CrowdFlower
Cohen’s Kappa: 0.62
Category labelsmore
Information Sharing
(49%
vs
22%)
less Me Now
(10%
vs
40%)
+ inclusion of organizations
compared to random sample in
Naaman
(2010)Slide21
RESULTS:
CategoriesPredictorQuestion to FollowersInformation Sharing
Self-Promotion
Random ThoughtOpinion / ComplaintMe NowConversationPresence MaintenanceSlide22
RESULTS:
CategoriesPredictorQuestion to Followers
Information Sharing
Self-PromotionRandom ThoughtOpinion / ComplaintMe NowConversation
Presence Maintenance
“
gud
morning twits
”
20%
liked
45%
dislikedSlide23
RESULTS:
CategoriesPredictorQuestion to Followers
Information Sharing
Self-PromotionRandom ThoughtOpinion / ComplaintMe NowConversation
Presence Maintenance
Odds Ratio
2.83
2.69
2.69
2.47
2.05
1.89
1.57
N/A
“
gud
morning twits
”
20%
liked
45%
disliked
*p<.01
˘trend p=.05Slide24
Odds Ratio
2.832.692.692.472.05
1.89
1.57N/A
RESULTS:
Categories
Predictor
Question to Followers
Information Sharing
Self-Promotion
Random Thought
Opinion / Complaint
Me Now
Conversation
Presence Maintenance
“What'd
they say?? @adam807 Dreamed I went to an @
waitwait
taping and they had to stop because a guest made @
petersagal
cry
.”
24%
liked
34%
disliked
*p<.01
˘trend p=.05Slide25
Odds Ratio
2.832.692.692.472.05
1.89
˘1.57N/A
RESULTS:
Categories
Predictor
Question to Followers
Information Sharing
Self-Promotion
Random Thought
Opinion / Complaint
Me Now
Conversation
Presence Maintenance
“
tired and upset
”
27%
liked
25%
disliked
*p<.01
˘trend p=.05Slide26
Odds Ratio
2.83*2.69*2.69*2.47*2.05˘
1.89
˘1.57N/A
RESULTS:
Categories
Predictor
Question to Followers
Information Sharing
Self-Promotion
Random Thought
Opinion / Complaint
Me Now
Conversation
Presence Maintenance
*p<.01
˘trend p=.05Slide27
Odds Ratio
2.83*2.69*2.69*2.47*2.05˘
1.89
˘1.57N/A
RESULTS:
Categories
Predictor
Question to Followers
Information Sharing
Self-Promotion
Random Thought
Opinion / Complaint
Me Now
Conversation
Presence Maintenance
*p<.01
˘trend p=.05Slide28
Odds Ratio
2.83*2.69*2.69*2.47*2.05˘
1.89
˘1.57N/A
RESULTS:
Categories
Predictor
Question to Followers
Information Sharing
Self-Promotion
Random Thought
Opinion / Complaint
Me Now
Conversation
Presence Maintenance
*p<.01
˘trend p=.05Slide29
Not Worth
ReadingRESULTS: ReasonsSlide30
Not Worth
ReadingOld News“Yes, I saw that first thing this morning.”“Since
your followers read the NYT too, reposting NYT URLs is tricky unless you add something.”
No Personal TouchConversations“Twitter’s fault; feels like listening in on a private conversation”
RESULTS:
ReasonsSlide31
Not Worth
ReadingBanal or ProsaicTweets“…and so what?”“Just links are the worst thing in the world.
”
Lack of ContextProfessional vs Personal Insight
“I
unfollowed
you for this tweet. I don’t know you; I followed you b/c of you job.”
No Curiosity
“All the news I need is here. Not much of a tease.”
RESULTS:
ReasonsSlide32
Worth
ReadingRESULTS: ReasonsSlide33
Worth
ReadingValued Information“interesting perspective on something I know nothing about.”“makes you want to know more.”
Appealing Description
Conciseness“few words to say much, very clear.”
Human
“personal, honest, and transparent.”
RESULTS:
ReasonsSlide34
Embed more context
in tweets (be less cryptic)Add extra commentary, especially if RTingUse twitter-specific mechanisms (hashtags, @mentions, and DMs) appropriately
Unique hashtag
for questions is valuedConciseness, even with 140 chars, valuedHappy sentiments valued; whining disliked
IMPLICATIONS FOR PRACTICESlide35
Exploring
different communities on TwitterWhich results generalizeRate author, not tweet
Users no longer followed
Self-ratingsTwitter as maintaining awareness and relationships
LIMITATIONS
FUTURE WORKSlide36
DISCUSSION
Utilizing results:Twitter’s simplicity vs. Facebook’s newsfeed complexityPresentation:
Technological
intervention:design tools to learn, filter, re-presentSocial intervention:
inform users of perceived value and reactionSlide37
Social media sites:
but also new questions of content value and accepted practicenew connection opportunitiesDesign sites to elicit more
subtle reactions
Sample of 1,400 users and 43,000 ratings:CONCLUSIONS41% of feed worth readingInformation Sharing
liked / Me Now disliked
Reasons:
context, commentary,
conciseness, …
Technological and social
interventionsSlide38
Social media sites:
but also new questions of content value and accepted practicenew connection opportunitiesDesign sites to elicit more
subtle reactions
Sample of 1,400 users and 43,000 ratings:41% of feed worth readingInformation Sharing liked / Me Now dislikedReasons:
context, commentary,
conciseness, …
Technological and social
interventions
CONCLUSIONS
CONCLUSIONS
CONCLUSIONS
Thanks for listening!
with thanks to Ed
Cutrell
, Robert Kraut, m.c. schraefel,
Ryen
White,
Sarita
Yardi
, HCII Social Comp. group and
a
nonymous reviewers
Paul André – CMU HCII
Michael Bernstein – MIT CSAIL
Kurt Luther – Georgia Tech GVUSlide39
RESULTS
CategoriesPredictor
Odds Ratio
z value
Question to Followers
2.83
2.94*
Information Sharing
2.69
3.05*
Self-Promotion
2.69
2.61*
Random Thought
2.47
2.89*
Opinion / Complaint
2.05
1.93˘
Me Now
1.89
1.94˘
Conversation
1.57
1.26
Presence Maintenance
N/A
N/ASlide40
RESULTS
CategoriesQuestion to FollowersInformation SharingSelf-PromotionRandom ThoughtOpinion / Complaint
Me Now
ConversationPresence Maintenance47% chance of being Worth Reading“This is a good use of Twitter.”“Gives one pause to think about the question posted.”
Questions to FollowersSlide41
RESULTS
CategoriesQuestion to FollowersInformation SharingSelf-PromotionRandom ThoughtOpinion / Complaint
Me Now
ConversationPresence Maintenance“The headline arouses my curiosity.”“Wow. Didn’t know that was happening.
Thanks for informing me.”
Information SharingSlide42
RESULTS
CategoriesQuestion to FollowersInformation SharingSelf-PromotionRandom ThoughtOpinion / Complaint
Me Now
ConversationPresence Maintenance22% chance of being Worth Reading“Sorry, but I don’t care what people are eating.”“Too much personal info.”“He moans about this ALL THE TIME. Seriously.”
Me NowSlide43
RESULTS
CategoriesQuestion to FollowersInformation SharingSelf-PromotionRandom ThoughtOpinion / Complaint
Me Now
ConversationPresence MaintenanceMe Now“
Foursquare updates don’t need to be shared on
Twitter
unless there’s a relevant update to be made.”
“4sq,
ffs
.”Slide44
RECRUITMENT