The Book of Trees is now available!      See other retailers
Home     About     VC Book     Stats     Blog     Books     Links     Contact  
Search the VC database:
    Knowledge Networks  
The materials shown on this page are copyright protected by
their authors and/or respective institutions.
Twitter Orographies
Data Interfaces
Project Description:
Twit­ter Oro­gra­phies is an exper­i­ment in the visu­al­iza­tion of Twit­ter con­ver­sa­tions targeting the dis­cus­sion space around a given key­word. It rep­re­sents the seman­tic space of top­ics that emerge, the rel­a­tive rel­e­vance of each topic, and the rela­tions between the dif­fer­ent top­ics that arise from the discussion.

Oper­a­tionally, Twit­ter Oro­gra­phies works by lis­ten­ing (in real time) to the stream of all the tweets that men­tion a given key­word (or hash­tag). Each one of these tweets is then ana­lyzed by remov­ing com­mon words with weak seman­tic con­tent (such as arti­cles and propo­si­tions) and the remain­ing words are added to a weighted net­work in which the dis­cus­sion top­ics are rep­re­sented by nodes (weighted by fre­quency) and weight of the edges rep­re­sent the relat­ed­ness of the top­ics (how often the two top­ics appear in the same tweet).

Once the final net­work is defined, the inter­face cre­ates a seman­tic land­scape out of the dis­cus­sion, in which the most rel­e­vant top­ics appear as higher moun­tains and the emerg­ing top­ics as lower hills, and where the relat­ed­ness is mapped to topic prox­im­ity and dis­played through the use of explicit visual links.

The oro­graphic metaphor allows to track the evo­lu­tion of smaller and big­ger land­forms that rep­re­sent spe­cific top­ics, moun­tain sys­tems that dis­play clus­ters of related top­ics, oro­grafic belts cre­ated by chains of given words (usu­ally caused by pseudo-retweets).

Comments (0):
*Note* Before you submit your comment, bear in mind there's no guarantee it will be seen by this project's author. In case you want to contact the author directly, please follow the provided URL.
Leave a Comment:
(We're looking for the best solution to avoid unwanted SPAM)
Manuel Lima |