Titulo Estágio
Retweet Predictive Model in Twitter
Área Tecnológica
Reconhecimento de Padrões
Local do Estágio
DEI - Departamento de Engenharia Informática
Enquadramento
Retweeting is the key mechanism to information diffusion in Twitter. As a means of disseminating useful information, it plays an important role to build recommendation engines for personalized Twitter streams. Even though a lot of information is shared via its social network structure in Twitter, little is known yet about how and why certain information spreads more widely than others.
Objetivo
The main goal is to build a retweet predictive model based on the properties extracted from Twitter streams. The model should empirically show how impact of factors (e.g. URLs, #Hashtags, etc.) influence retweeting predictability.
The idea is that recommendations and personalization should help to optimize the information diffusion that already naturally occurs in the Twitter network. The retweet predictive model would enable users to catch interesting items that might have missed in a large number of tweets.
Plano de Trabalhos - Semestre 1
1) State-of-the art review of Microblogging and Twitter social networks, Sept 2013
2) Features Extraction in Twitter social networks streams Sep-Oct 2013
3) Exploratory analysis in retweeting data and preliminary tests Nov-Dec 2013
4) Intermediate report and plan of possible extensions or alternatives: Jan 2013
Plano de Trabalhos - Semestre 2
1) Development of a Predictive Retweet Model Feb-May 2013
2) Tests and analysis of factors impacting retweet in Twitter network Mar-May 2013
3) Thesis Report May-Jun 2013
Condições
Strong skills in programming (Java, Python, C/C++).
Other interesting (optional) skills/interests include Machine Learning and Pattern Recognition
Orientador
Bernardete Ribeiro e Catarina Silva
bribeiro@dei.uc.pt 📩