Options
Synthetic Dataset Generation for Online Topic Modeling
Author(s)
Date Issued
2018-04-12
Date Available
2019-07-03T07:45:47Z
Abstract
Online topic modeling allows for the discovery of the underlying latent structure in a real time stream of data. In the evaluation of such approaches it is common that a static value for the number of topics is chosen. However, we would expect the number of topics to vary over time due to changes in the underlying structure of the data, known as concept drift and concept shift. We propose a semi-synthetic dataset generator, which can introduce concept drift and concept shift into existing annotated non-temporal datasets, via user-controlled paramaterization. This allows for the creation of multiple different artificial streams of data, where the “correct” number and composition of the topics is known at each point in time. We demonstrate how these generated datasets can be used as an evaluation strategy for online topic modeling approaches.
Sponsorship
Science Foundation Ireland
Other Sponsorship
Insight Research Centre
Type of Material
Conference Publication
Publisher
CEUR-WS.org
Start Page
63
End Page
75
Copyright (Published Version)
2017 the Author
Web versions
Language
English
Status of Item
Peer reviewed
Part of
McAuley, J., McKeever, S. (eds.). Proceedings of the 25th Irish Conference on Artificial Intelligence and Cognitive Science, Dublin, Ireland, December 7 - 8, 2017
Conference Details
AICS 2017: 25th Irish Conference on Artificial Intelligence and Cognitive Science, Dublin, Ireland, 7 - 8 December 2017
This item is made available under a Creative Commons License
File(s)
Owning collection
Views
518
Last Month
1
1
Acquisition Date
Mar 27, 2024
Mar 27, 2024
Downloads
267
Last Month
3
3
Acquisition Date
Mar 27, 2024
Mar 27, 2024