It’s well-known that Twitter’s most powerful use is as tool for real-time journalism. Trying to understand its social connections and outstanding capacity to propagate information, we have developed a mathematical model to identify the evolution of a single tweet.
The way a tweet is spread through the network is closely related with Twitter’s retweet functionality, but retweet information is fairly incomplete due to the fight for earning credit/users by means of being the original source/author. We have taken into consideration this behavior and our approach uses text similarity measures as complement of retweet information. In addition, #hashtags and urls are included in the process since they have an important role in Twitter’s information propagation.
Once we designed (and implemented) our mathematical model, we tested it with some Twitter’s topics we had tracked using a visualization tool (Life of a Tweet) . Our conclusiones after the experiments were:
- Twitter’s real propagation is based on information (tweets’ content) and not on Twitter’s structure (retweet).
- Based on we can detect Twitter’s real propagation, we can retrieve Twitter’s real networks.
- Text similarity scores allow us to select how fuzzy are the tweet’s connections and, in extension, the network’s connections. This means that we can set a minimun threshold to determine when two tweets contain the same concept.
Libya war data structure is a huge and self-connected network. Across this structure, we have obtained the life of several tweets. Using a 30% of similarity, we have been able to observe, in one hand, how some information about news and events mute and change, and in the other hand, another information like lemmas prevail unchanged in the time.
Original: @BreakingNews “gadhafi’s wife, daughter have crossed into tunisia from libya, tunisian security tells reuters” (See on Twitter)
Mutation: @felix85 “Reuters: Gaddafi’s wife and his daughter aisha have crossed into tunisia from libya – tunisian security source” (See on Twitter)
Mutation: @SkyNewsBreak “Reuters: Colonel Gaddafi’s wife and daughter cross border from Libya into Tunisia” (See on Twitter)
Original: @NicRobertsonCNN “According to two sources, Libyan rape victim Eman al Obeidi has been forcibly deported from Qatar to Eastern Libya” (See on Twitter)
Mutation: @AltMuslimah “Alleged Libyan rape victim deported from Qatar back to Libya | Says she was beaten and forced onto a plane in Qatar #cnn http://t.co/Fesxfag” (See on Twitter)
Mutation: @Krank_IE “Eman al-Obeidi has been forcibly returned to Libya from Qatar via @storyful. http://storyful.com/stories/gjdk44 #emanalobeidi” (See on Twitter)
Original: @BreakingNews “House adopts resolution rebuking Obama foraction against Libya without congressional approval – AP http://on.msnbc.com/jent66″ (See on Twitter)
Mutation: @beesnguns “boehner to introduce resolution tomorrow demanding that obama seek congressional approval on libya” (See on Twitter)
Mutation: @LVview “US House non-binding resolution criticizes Obama 4 military action in Libya w/out Congressional approval. Asks for rationale, scope & costs.” (See on Twitter)
Mutation: @AP “Republicans, Democrats scold Obama for sending U.S. forces against Libya without congressional approval: http://apne.ws/mEXBHg -RJJ” (See on Twitter)
Mutation: @GOPnews “Wise Republic: House Adopts Resolution Rebuking Obama on Libya http://bit.ly/kCRfKP” (See on Twitter)
Original: @PartiPirate “If your government shuts down the Internet, shut down your government. http://twitpic.com/5705t9 #iran #egypt #bahrain #libya #syria #rev11″ (See on Twitter)
In this case, we observed that “lemmas” had less mutations, and the tweet modification only affected to #hashtags and urls
We provide a “cut in the edge” software capable to track several hashtags, process the information related, create the structures and show in one click the main results. We show some screeshots:
- Main statistics tool: Picture shows the life of a tweets representing the number of tweets per time unit.
- Timeline tool: We can navigate across time in order to work with real tweets information: user, text, time, followers, ..
- Map tool : We can see the geo tweet distribution in a map.
- Graph tool: The above picture, shows the retweet information for a determinate thread (a thread is a text and its associated information)
Related reading: Mining the Social Web: Analyzing Data from Facebook, Twitter, LinkedIn, and Other Social Media Sites | Controllability of complex networks