Presentation is loading. Please wait.

Presentation is loading. Please wait.

W HO G IVES A T WEET ? Evaluating Microblog Content Value Paul Michael Bernstein Kurt Luther Carnegie Mellon & Uni. Southampton MIT CSAIL.

Similar presentations


Presentation on theme: "W HO G IVES A T WEET ? Evaluating Microblog Content Value Paul Michael Bernstein Kurt Luther Carnegie Mellon & Uni. Southampton MIT CSAIL."— Presentation transcript:

1 W HO G IVES A T WEET ? Evaluating Microblog Content Value Paul André @paulesque Michael Bernstein Kurt Luther Carnegie Mellon & Uni. Southampton MIT CSAIL Georgia Institute of Technology

2

3

4

5

6

7 ?

8 ? What content is valued, and why?

9 ? 1. design implications 2. emerging norms and practice

10 DESIGN Who Gives a Tweet? anonymous feedback from followers and strangers (analysis of follower ratings only)

11 DESIGN anticipated reciprocity Who Gives a Tweet? anonymous feedback from followers and strangers rate tweets (provide us data) receive value in return (ratings from followers)

12 DESIGN wgat_user: username:

13 RECRUITMENT

14

15

16 1,443 users rated 43,738 tweets from 21,014 Twitter accounts

17 entire dataset RESULTS 36% Worth Reading 39% Neutral 25% Not Worth Reading 41% Worth Reading average user

18 What content is valued, and why?

19 What content is valued, and why? 1. categories 2. reasons why

20 What content is valued, and why? 4,220 tweets Ground truth + CrowdFlower Cohens Kappa: 0.62 Category labels more Information Sharing (49% vs 22%) less Me Now (10% vs 40%) + inclusion of organizations compared to random sample in Naaman (2010)

21 RESULTS: Categories Predictor Question to Followers Information Sharing Self-Promotion Random Thought Opinion / Complaint Me Now Conversation Presence Maintenance

22 RESULTS: Categories Predictor Question to Followers Information Sharing Self-Promotion Random Thought Opinion / Complaint Me Now Conversation Presence Maintenance gud morning twits 20% liked 45% disliked

23 RESULTS: Categories Predictor Question to Followers Information Sharing Self-Promotion Random Thought Opinion / Complaint Me Now Conversation Presence Maintenance Odds Ratio 2.83 2.69 2.47 2.05 1.89 1.57 N/A gud morning twits 20% liked 45% disliked *p<.01 ˘trend p=.05

24 Odds Ratio 2.83 2.69 2.47 2.05 1.89 1.57 N/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=.05

25 Odds Ratio 2.83 2.69 2.47 2.05 1.89˘ 1.57 N/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=.05

26 Odds Ratio 2.83* 2.69* 2.47* 2.05˘ 1.89˘ 1.57 N/A RESULTS: Categories Predictor Question to Followers Information Sharing Self-Promotion Random Thought Opinion / Complaint Me Now Conversation Presence Maintenance *p<.01 ˘trend p=.05

27 Odds Ratio 2.83* 2.69* 2.47* 2.05˘ 1.89˘ 1.57 N/A RESULTS: Categories Predictor Question to Followers Information Sharing Self-Promotion Random Thought Opinion / Complaint Me Now Conversation Presence Maintenance *p<.01 ˘trend p=.05

28 Odds Ratio 2.83* 2.69* 2.47* 2.05˘ 1.89˘ 1.57 N/A RESULTS: Categories Predictor Question to Followers Information Sharing Self-Promotion Random Thought Opinion / Complaint Me Now Conversation Presence Maintenance *p<.01 ˘trend p=.05

29 Not Worth Reading RESULTS: Reasons

30 Not Worth Reading Old 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 Touch Conversations Twitters fault; feels like listening in on a private conversation RESULTS: Reasons

31 Not Worth Reading Banal or Prosaic Tweets …and so what? Just links are the worst thing in the world. Lack of Context Professional vs Personal Insight I unfollowed you for this tweet. I dont 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: Reasons

32 Worth Reading RESULTS: Reasons

33 Worth Reading Valued 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: Reasons

34 Embed more context in tweets (be less cryptic) Add extra commentary, especially if RTing Use twitter-specific mechanisms (hashtags, @mentions, and DMs) appropriately Unique hashtag for questions is valued Conciseness, even with 140 chars, valued Happy sentiments valued; whining disliked IMPLICATIONS FOR PRACTICE

35 Exploring different communities on Twitter Which results generalize Rate author, not tweet Users no longer followed Self-ratings Twitter as maintaining awareness and relationships LIMITATION S FUTURE WORK

36 DISCUSSIO N Utilizing results: Twitters simplicity vs. Facebooks newsfeed complexity Presentation: Technological intervention: design tools to learn, filter, re-present Social intervention: inform users of perceived value and reaction

37 Social media sites: but also new questions of content value and accepted practice new connection opportunities Design sites to elicit more subtle reactions Sample of 1,400 users and 43,000 ratings: CONCLUSIONS 41% of feed worth reading Information Sharing liked / Me Now disliked Reasons: context, commentary, conciseness, … Technological and social interventions

38 Social media sites: but also new questions of content value and accepted practice new connection opportunities Design sites to elicit more subtle reactions Sample of 1,400 users and 43,000 ratings: 41% of feed worth reading Information Sharing liked / Me Now disliked Reasons: context, commentary, conciseness, … Technological and social interventions CONCLUSIONS Thanks for listening! with thanks to Ed Cutrell, Robert Kraut, m.c. schraefel, Ryen White, Sarita Yardi, HCII Social Comp. group and anonymous reviewers Paul André – CMU HCII Michael Bernstein – MIT CSAIL Kurt Luther – Georgia Tech GVU

39 RESULTS Categories PredictorOdds Ratioz value Question to Followers2.832.94* Information Sharing2.693.05* Self-Promotion2.692.61* Random Thought2.472.89* Opinion / Complaint2.051.93˘ Me Now1.891.94˘ Conversation1.571.26 Presence MaintenanceN/A

40 RESULTS Categories Question to Followers Information Sharing Self-Promotion Random Thought Opinion / Complaint Me Now Conversation Presence Maintenance 47% chance of being Worth Reading This is a good use of Twitter. Gives one pause to think about the question posted. Questions to Followers

41 RESULTS Categories Question to Followers Information Sharing Self-Promotion Random Thought Opinion / Complaint Me Now Conversation Presence Maintenance The headline arouses my curiosity. Wow. Didnt know that was happening. Thanks for informing me. Information Sharing

42 RESULTS Categories Question to Followers Information Sharing Self-Promotion Random Thought Opinion / Complaint Me Now Conversation Presence Maintenance 22% chance of being Worth Reading Sorry, but I dont care what people are eating. Too much personal info. He moans about this ALL THE TIME. Seriously. Me Now

43 RESULTS Categories Question to Followers Information Sharing Self-Promotion Random Thought Opinion / Complaint Me Now Conversation Presence Maintenance Me Now Foursquare updates dont need to be shared on Twitter unless theres a relevant update to be made. 4sq, ffs.

44 RECRUITMENT


Download ppt "W HO G IVES A T WEET ? Evaluating Microblog Content Value Paul Michael Bernstein Kurt Luther Carnegie Mellon & Uni. Southampton MIT CSAIL."

Similar presentations


Ads by Google