Your SlideShare is downloading. ×
0
Exploring the Streams of Online
Community Conversation:
Insights into the Twitterverse
@stephendann
Australian National Un...
Usual House Rules
@stephendann for questions
#anzmac13 for commentary
A little context
The Past
• Dann (2010)
– Six top level twitter
categories
– 23 sub domains
• Dann (2011)
– Six top level
...
Twitter Analysis 2.0.14
The Procedure
Acquire Research Question
• Does Event X change the tweeting patterns of Account @Y?
• Do responses to the #hashtag event ...
Acquire your data
• Personal timelines
– Download from Twitter
• #Hashtag captures
– Hootsuite
• Time line captures
– Choo...
Big Data
• If you are Axel Bruns, fine, continue
– http://mappingonlinepublics.net/
• For everyone else, what are you look...
Process your data
• Stand by for ugliness and manual coding*
– Extract data into Excel
• Excel allows for additional data ...
Manual Coding
• Use the Dann (2010) or Dann (2011) top level
domains
– Dann (201X) is under development
• I broke somethin...
Pick a box
1 Conversational Uses an @statement to address another user
2 News Events Identifiable news content
3 Pass alon...
Keep it on manual
Conversational Uses an @statement to address another user
1.1 Action
Activities involving other Twitter ...
Upgrades
Pass along Tweets of endorsement of content
3.1 Automated
Endorsement Status announcements triggered by third par...
Speed Hacking Excel
• Speed hacks exist
– Alphabet Tweet Sort
• @, RT, MT cluster
• “Find all” selecting.
Coding Time!
• Cross check the coding
– Some variance is okay
– Resolve it through the
usual traditions
Sample Data #qldquake
Coded
Analysis Table Block
Category
Tweet
(TCat)
Tweet
Ratio
Max
Density
Actual
Characters
Character
Density
Density
Ratio
Conve...
Tweet Math Dude
• Tweet Count
– N per category
• Calculate the Tweet Ratio
– Tweet ratio is a normalized rank order of the...
Maximum Character Density
• Max Density = 140 x TCat [number of tweets in
each category]
• Theoretical range for a tweet i...
Reporting the Data
Category
Tweet
(TCat)
Tweet
Ratio
Max
Density
Actual
Characters
Character
Density
Density
Ratio
Convers...
Reporting the Data
0
0.2
0.4
0.6
0.8
1
1.2
Conversational
News
Pass Along
Phatic
Spam
Status
Ratio Density
Text Analysis Wave 1
Linguistic Inquiry Word Count
So. Very. Fast.
LIWC
• http://www.liwc.net/
– text analysis software
– calculates the degree to which people use
different categories of w...
A giant bucket of data
• 70 variables
– So have a hypothesis and a purpose for the
analysis
• Differences in tweet constru...
Results
Average Word Count (AWC) Unique Word Count (UWC)
Category AWC AWC_Ratio
Conversational
12.82 0.78
News 13.56 0.82
...
Results
Word Count Unique Word
0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
Conversational
News
Pass AlongPhatic
Status
0.93
0....
Text Analysis Wave 2
Leximancer
Leximancer
• Import into Leximancer as an individual
analysis (individual project)
– Edit Pre processing options: Sentence...
Map time!
Four sample maps
Entirely because quadrants fit on screens better than hexes. No other reason
conversational
news
pass alo...
Tweet Network Density
• Calculate Network Density
– Count Nodes (n)
– Count Actual Connections (e) Edges (paths
between no...
Pass Along Network
Nodes Edges Network Density
15 15 0.14
Network Density Results
Category Nodes Edges
Network
Density
Conversational 13 12 0.15
News 18 17 0.11
Pass Along 15 15 0....
One Bucket of Data
• This is why a research question is important
– You can map a range of information
– None of it is use...
Questions?
• @stephendann
• Stephen.dann@anu.edu.au
• stephen@stephendann.net
Upcoming SlideShare
Loading in...5
×

Insights into the Twitterverse: Benchmarking and analysis twitter content

550

Published on

The 2014 Remix of the Twitter Content Classification framework now featuring statistics, radar plots, Linguistic Inquiry Word Count, Leximancer, network plots and more opportunities to run maths, stats and graphs than ever before.

Published in: Business
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total Views
550
On Slideshare
0
From Embeds
0
Number of Embeds
1
Actions
Shares
0
Downloads
5
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

Transcript of "Insights into the Twitterverse: Benchmarking and analysis twitter content"

  1. 1. Exploring the Streams of Online Community Conversation: Insights into the Twitterverse @stephendann Australian National University
  2. 2. Usual House Rules @stephendann for questions #anzmac13 for commentary
  3. 3. A little context The Past • Dann (2010) – Six top level twitter categories – 23 sub domains • Dann (2011) – Six top level – 28 sub domain The Present • Dann (Today) – Six Top Level Categories • No sub domain analysis – Secondary Processing • Leximancer • Linguistic Inquiry Word Count
  4. 4. Twitter Analysis 2.0.14 The Procedure
  5. 5. Acquire Research Question • Does Event X change the tweeting patterns of Account @Y? • Do responses to the #hashtag event change over time? – #EventTags in Time Period A will have more Status than in Time Period D – Time Period D will have more Pass Along than Status • What were they thinking? – Dominant Categories of tweets over time within a selected account • Do comments change by platform for account @X? – mobile versus web versus desktop • Does @BrandX engage with the community? – Conversational over all other types over capture time period
  6. 6. Acquire your data • Personal timelines – Download from Twitter • #Hashtag captures – Hootsuite • Time line captures – Choose your own adventure – Getting worse, harder and Twitter’s API is less available. • Try to avoid big data
  7. 7. Big Data • If you are Axel Bruns, fine, continue – http://mappingonlinepublics.net/ • For everyone else, what are you looking for? – What sample suits your research question?
  8. 8. Process your data • Stand by for ugliness and manual coding* – Extract data into Excel • Excel allows for additional data inputs as you progress the analysis – Keep tweet visible • Only keep a column visible if it fits your research question – Eg date, time, @user, platform – Add column for Tweet ID, category, cat_n • Sub category, sub_cat_n for the detailed version *Automated coding? People are working on it. It’s a terrible idea that’ll happen anyway
  9. 9. Manual Coding • Use the Dann (2010) or Dann (2011) top level domains – Dann (201X) is under development • I broke something important earlier this year • Manual coding is superior – Nuance and interpretation counts.
  10. 10. Pick a box 1 Conversational Uses an @statement to address another user 2 News Events Identifiable news content 3 Pass along Tweets of endorsement of content 4 Phatic Content independent connected presence 5 Status Tweets which address the statement "What are you doing?" and "What's happening?" in terms of an account holder's experiences 6 Spam Unsolicited content
  11. 11. Keep it on manual Conversational Uses an @statement to address another user 1.1 Action Activities involving other Twitter users, or tweets which describe the presence of other Twitter users. 1.2 Query Any statement style tweet that ends with a question mark, as it represents an active attempt to engage responses from the community 1.3 Referral An @response which contains URLs or recommendation of other Twitter users. (Excludes RT @user) 1.4 Response Classification for tweets which commence with another user’s name and which do not meet the requirements of the referral category 1.5 Rhetoric Question Asked and answered within the same tweet (distinct from Conversational - Query) which may not require (but may elicit) audience response
  12. 12. Upgrades Pass along Tweets of endorsement of content 3.1 Automated Endorsement Status announcements triggered by third party applications which publish URLs 3.2 Endorsement Links to web content not created by the sender 3.3 Retweet Any statement reproducing another Twitter status using the via @ or RT protocol 3.4 Secondary Social Media Links to Facebook (fb.me) or similar social media platform 3.5 User generated content Links to own content created by the user 3.6 Quote Comment marked with “ “ to represent a direct quote, paraphrase of a statement without a source URL, including reference to offline speaker or overheard (OH) 3.7 Cite Any tweet which contains a reference in a recognised Harvard, Oxford or similar format 3.8 Modified ReTweet Acknowledgement of the use of MT protocol to allow for an edited RT.
  13. 13. Speed Hacking Excel • Speed hacks exist – Alphabet Tweet Sort • @, RT, MT cluster • “Find all” selecting.
  14. 14. Coding Time! • Cross check the coding – Some variance is okay – Resolve it through the usual traditions
  15. 15. Sample Data #qldquake
  16. 16. Coded
  17. 17. Analysis Table Block Category Tweet (TCat) Tweet Ratio Max Density Actual Characters Character Density Density Ratio Conversational News Pass Along Phatic Spam Status n
  18. 18. Tweet Math Dude • Tweet Count – N per category • Calculate the Tweet Ratio – Tweet ratio is a normalized rank order of the highest volume of tweets, where the most common category is scored as 1 • Calculating the Tweet Ratio – Highest number of tweets in a single category = TTMax – Tweets per category = TCat – Ratio is Tcat / TTMax I’m only mildly mocking statistical analysis here
  19. 19. Maximum Character Density • Max Density = 140 x TCat [number of tweets in each category] • Theoretical range for a tweet is between 1 and 140 characters • Maximum tweet is 140 characters • More characters used, more information density • Calculate Character Density – (Actual Character / Max Density) • Divide each CharDensity score by the highest Char density • Normalise CharDensity score to rank order
  20. 20. Reporting the Data Category Tweet (TCat) Tweet Ratio Max Density Actual Characters Character Density Density Ratio Conversational 39 0.08 5460 3533 65% 0.81 News 41 0.08 5740 3778 66% 0.83 Pass Along 481 1 67340 53491 79% 1.00 Phatic 21 0.04 2940 2179 74% 0.93 Spam 1 0.00 140 81 58% 0.73 Status 18 0.03 2520 1543 61% 0.77 n 601 84140 64605 77%
  21. 21. Reporting the Data 0 0.2 0.4 0.6 0.8 1 1.2 Conversational News Pass Along Phatic Spam Status Ratio Density
  22. 22. Text Analysis Wave 1 Linguistic Inquiry Word Count So. Very. Fast.
  23. 23. LIWC • http://www.liwc.net/ – text analysis software – calculates the degree to which people use different categories of words in texts • 70 other language dimensions. – positive or negative emotions, – self-references, – causal words,
  24. 24. A giant bucket of data • 70 variables – So have a hypothesis and a purpose for the analysis • Differences in tweet construction – Word Counts – Unique Words
  25. 25. Results Average Word Count (AWC) Unique Word Count (UWC) Category AWC AWC_Ratio Conversational 12.82 0.78 News 13.56 0.82 Pass Along 16.35 1 Phatic 15.42 0.94 Status 12.94 0.79 Category UWC UWC_Ratio Conversational 93 0.97 News 93 0.97 Pass Along 92 0.96 Phatic 93 0.97 Status 96 1
  26. 26. Results Word Count Unique Word 0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1 Conversational News Pass AlongPhatic Status 0.93 0.94 0.95 0.96 0.97 0.98 0.99 1 Conversational News Pass AlongPhatic Status Chart Title
  27. 27. Text Analysis Wave 2 Leximancer
  28. 28. Leximancer • Import into Leximancer as an individual analysis (individual project) – Edit Pre processing options: Sentence per block 1 – Run to Generate Outputs – Generate Concept Map
  29. 29. Map time!
  30. 30. Four sample maps Entirely because quadrants fit on screens better than hexes. No other reason conversational news pass along phatic
  31. 31. Tweet Network Density • Calculate Network Density – Count Nodes (n) – Count Actual Connections (e) Edges (paths between nodes) – Calculate Network density based on 2e / n(n-1) • Network Density Notes – Calculate potential connections
  32. 32. Pass Along Network Nodes Edges Network Density 15 15 0.14
  33. 33. Network Density Results Category Nodes Edges Network Density Conversational 13 12 0.15 News 18 17 0.11 Pass Along 15 15 0.14 Phatic 3 2 0.67 Status 4 3 0.50 n 19 17 0.10 0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 Conversational News Pass AlongPhatic Status
  34. 34. One Bucket of Data • This is why a research question is important – You can map a range of information – None of it is useful without the RQ / hypothesis – It’s pretty, but not valuable Category Tweet Density Network Ave.WC Unique Words Conversatio nal 0.081081 0.819075 0.814598 0.830959 0.96875 News 0.085239 0.83315 0.828595 0.878952 0.96875 Pass Along 1 1.005496 1 1.059722 0.958333 Phatic 0.043659 0.938173 0.933044 1 0.96875 Status 0.037422 0.775065 0.770829 0.838992 1 0 0.2 0.4 0.6 0.8 1 1.2 Tweet Density Network Ave.WC Unique Words Chart Title Conversational News Pass Along Phatic Status
  35. 35. Questions? • @stephendann • Stephen.dann@anu.edu.au • stephen@stephendann.net
  1. A particular slide catching your eye?

    Clipping is a handy way to collect important slides you want to go back to later.

×