Chorus as a tool for facilitating learning in social media analytics - Philip Brooker

1,057 views

Published on

Presentation given at the HEA Social Sciences learning and teaching summit 'Exploring the implications of ‘the era of big data’ for learning and teaching'.

A blog post outlining the issues discussed at the summit is available via: http://bit.ly/1lCBUIB

Published in: Education
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total views
1,057
On SlideShare
0
From Embeds
0
Number of Embeds
760
Actions
Shares
0
Downloads
2
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

Chorus as a tool for facilitating learning in social media analytics - Philip Brooker

  1. 1. Chorus is a social media harvesting and visual analytic suite designed to facilitate and enable social science research using Twitter data, and is free to use and download via the Chorus website (www.chorusanalytics.co.uk). Chorus is the product of an interdisciplinary collaboration of information and computing scientists and researchers from the social sciences, and comprises two programs: Chorus-TCD automates the process of retrieving data, requiring minimal input from users, and allows users to take control of their own data collection with full compliance to the Twitter T&Cs. There are two data collection strategies available: Query Keyword searches allows users to input terms to collect data that matches a set of linguistic criteria, accumulating data around usages of those terms. User-Following searches allow users to follow the timelines of lists of specified Twitter usernames. Chorus-TV is a powerful visual analytic suite which allows users to drill down into their datasets with an array of visual representations and metrics. The Timeline Explorer (above) allows users to trace the ebbs and flows of Twitter talk across time, featuring various metrics such as sentiment analysis and homogeneity/novelty measures. The Cluster Explorer (below) provides a non-time- dependent view of the data via a series of cluster maps which visualise topics as linked clusters of semantically-related terms.

×