Topic models for conference session assignment: Organising PR AS A 2014(5)

Michael Burke, Deon Sabatta

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Conference scheduling and organisation is a particularly laborious task and can be extremely time consuming. While many online conference platforms allow manual topic selection, these can be expensive and typically still require that individual papers be scanned and labelled appropriately before being assigned to reviewers and relevant conference tracks or sessions. This paper shows how the bulk of this process can be automated using topic models. Latent Dirichlet allocation is applied to learn conference topics directly from documents, and a clustering algorithm introduced to separate these into suitably sized conference sessions, determining an appropriate session topic in the process. Conference tracks can then be scheduled by maximising the distance between these session topics, thereby avoiding potential topic conflicts in parallel tracks.
Original languageEnglish
Title of host publication2015 Pattern Recognition Association of South Africa and Robotics and Mechatronics
Place of PublicationPort Elizabeth, South Africa
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages94-99
Number of pages6
ISBN (Electronic)978-1-4673-7450-7
DOIs
Publication statusPublished - 17 Dec 2015
Event2015 Pattern Recognition Association of South Africa and Robotics and Mechatronics International Conference (PRASA-RobMech) - Port Elizabeth, South Africa
Duration: 26 Nov 201527 Nov 2015
https://robmechprasa2015.mandela.ac.za/

Conference

Conference2015 Pattern Recognition Association of South Africa and Robotics and Mechatronics International Conference (PRASA-RobMech)
Abbreviated titlePRASA-RobMech 2015
CountrySouth Africa
CityPort Elizabeth
Period26/11/1527/11/15
Internet address

Fingerprint Dive into the research topics of 'Topic models for conference session assignment: Organising PR AS A 2014(5)'. Together they form a unique fingerprint.

Cite this