The social media services that have emerged over the past decade have changed the way in which many of us communicate. Consequently, they became an object of various data analyses, such as information extraction and summarization, social network analysis, opinion mining, among others. The data behind these services is vast and keeps growing at immense speed from day to day.
Twitter is one of the greatest examples and as a micro-blogging platform has vast potential to become a collective source of intelligence that can be used to obtain opinions, ideas, facts, and sentiments.
This project aims to extend the work being developed in the TwitterEcho II project, through the design and integration of a data analytics layer into the current TwitterEcho research platform. The project will initially focus on integrating existing text and social network analysis modules (text pre-processing filters, language classification, opinion mining, topic modelling and influencers detection) into the TwitterEcho architecture and technologies (hadoop-based). The project will also focus on the development of data visualisations for charactering activity patterns and user behavior in Twitter communities.
Atividade deste projeto