Browse DORAS
Browse Theses
Search
Latest Additions
Creative Commons License
Except where otherwise noted, content on this site is licensed for use under a:

TriVis: visualising multivariate data from sentiment analysis

Doyle, Maryanne and Smeaton, Alan F. and Bermingham, Adam (2014) TriVis: visualising multivariate data from sentiment analysis. In: 8th Annual Irish Human Computer Interaction (iHCI) conference, 1-2 Sept 2014, DCU, Dublin, Ireland.

Full text available as:

[img]
Preview
PDF (Paper) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
414Kb
[img]
Preview
PDF (Poster) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
3557Kb

Abstract

In a time when a single sporting event can elicit millions of Tweets the volume of expressions of sentiment available is far too large to be read by an individual in real time. TriVis is a visualisation design that uses a modified scatter plot with three axes to allow the user to read and understand multidimensional data at a glance. We examined the readability of the visualisation using data collected from a golf tournament and plotted the sentiment towards golfers in real time during play. TriVis visualisations are simple, easy to understand and offer insights into obvious using other methods.

Item Type:Conference or Workshop Item (Poster)
Event Type:Conference
Refereed:Yes
Uncontrolled Keywords:Sentiment analysis; Social media analysis; Sports
Subjects:Computer Science > Interactive computer systems
Computer Science > Computational linguistics
Computer Science > Visualization
Computer Science > World Wide Web
DCU Faculties and Centres:Research Initiatives and Centres > INSIGHT Centre for Data Analytics
DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
ID Code:20145
Deposited On:19 Sep 2014 13:58 by Adam Bermingham. Last Modified 19 Sep 2014 13:58

Download statistics

Archive Staff Only: edit this record