Dunne, Jonathan and Malone, David and Penrose, Andrew (2018) Bundles: A Framework to Optimise Topic Analysis in Real-Time Chat Discourse. In: Dunne J., Malone D., Penrose A. (2018) Bundles: A Framework to Optimise Topic Analysis in Real-Time Chat Discourse. In: Rodrigues A., Fonseca B., Preguiça N. (eds) Collaboration and Technology. CRIWG 2018. Lecture Notes in Computer Science, vol 11001. Spr. Lecture Notes in Computer Science (LNCS) (11001). Springer, pp. 60-75. ISBN 9783319995045

Preview

Download (602kB) | Preview

Abstract

Collaborative chat tools and large text corpora are ubiquitous in today’s world of real-time communication. As micro teams and start-ups adopt such tools, there is a need to understand the meaning (even at a high level) of chat conversations within collaborative teams. In this study, we propose a technique to segment chat conversations to increase the number of words available (19% on average) for text mining purposes. Using an open source dataset, we answer the question of whether having more words available for text mining can produce more useful information to the end user. Our technique can help microteams and start-ups with limited resources to efficiently model their conversations to afford a higher degree of readability and comprehension.

Item Type:	Book Section
Additional Information:	This is the postprint version of the published article, which is available at Dunne J., Malone D., Penrose A. (2018) Bundles: A Framework to Optimise Topic Analysis in Real-Time Chat Discourse. In: Rodrigues A., Fonseca B., Preguiça N. (eds) Collaboration and Technology. CRIWG 2018. Lecture Notes in Computer Science, vol 11001. Springer, Cham. https://doi.org/10.1007/978-3-319-99504-5_6
Keywords:	chat segmentation; topic modelling; regression;
Academic Unit:	Faculty of Science and Engineering > Research Institutes > Hamilton Institute Faculty of Science and Engineering > Mathematics and Statistics
Item ID:	13362
Identification Number:	https://doi.org/10.1007/978-3-319-99504-5_6
Depositing User:	Dr. David Malone
Date Deposited:	02 Oct 2020 14:41
Publisher:	Springer
Refereed:	Yes
URI:	Publisher
Use Licence:	This item is available under a Creative Commons Attribution Non Commercial Share Alike Licence (CC BY-NC-SA). Details of this licence are available here

Repository Staff Only(login required)

Item control page

Downloads

Origin of downloads