Tweets Visualisation

Predictive analysis and visualisation from tweets

Presented by

Anh Hung Tuan
Quang Hiep Trinh
Anh Tuan Tran
Shibbir Hossain
Zhenyu Hu

Objective

Visualising tweets by integrating the online knowledge base

Progress

Literature review
Collect data using api and developed noise removal algorithm
Develop topic Modelling algorithm for Tweets by using online knowledge base
Visualisation of interrelated Topics using dummy data

Elaboration

Connect Twitter API
Collect data
Noise removal
- spelling
- by location
- language
- urban dictionary
- remove stop words

Topic Modelling

Latent Dirichlet allocation
Corpus : Wikipedia
- refine corpus
- words by popularity : observable feature
building a model: stimuli- noun/verbs

Demonstration

http://www.trial.net.au

Reference

[1] A. Guille and C. Favre, "Event detection, tracking, and visualization in twitter: a mention-anomaly-based approach," Social Network Analysis and Mining, vol. 5, no. 1, p. 18, 2015.

[2] D. Ghosh and R. Guha, "What are we ‘tweeting’about obesity? Mapping tweets with topic modeling and Geographic Information System," Cartography and geographic information science, vol. 40, no. 2, pp. 90-102, 2013.