Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/78363
DC FieldValue
dc.titleSummarization of corporate risk factor disclosure through topic modeling
dc.contributor.authorBao, Y.
dc.contributor.authorDatta, A.
dc.date.accessioned2014-07-04T03:15:27Z
dc.date.available2014-07-04T03:15:27Z
dc.date.issued2012
dc.identifier.citationBao, Y.,Datta, A. (2012). Summarization of corporate risk factor disclosure through topic modeling. International Conference on Information Systems, ICIS 2012 1 : 701-719. ScholarBank@NUS Repository.
dc.identifier.isbn9781627486040
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/78363
dc.description.abstractIn this paper, we propose a novel problem of summarizing textual corporate risk factor disclosure, which aims to simultaneously infer the risk types across corpus and assign each risk factor to its most probable risk type. To solve the problem, we develop a variation of LDA topic model called Sent-LDA. The variational EM learning algorithm, which guarantees fast convergence, is derived and implemented for our model. Experiments show that our model is much more efficient and effective than LDA for solving our proposed problem. Specifically, our model is 50 times faster than LDA in the same conditions, and generates better topics for summarization than LDA. Our model is visualized in a publicly available system.
dc.sourceScopus
dc.subjectRisk factor disclosure
dc.subjectSummarization
dc.subjectTopic modeling
dc.subjectVariational EM
dc.typeConference Paper
dc.contributor.departmentINFORMATION SYSTEMS
dc.description.sourcetitleInternational Conference on Information Systems, ICIS 2012
dc.description.volume1
dc.description.page701-719
dc.identifier.isiutNOT_IN_WOS
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

Page view(s)

204
checked on Aug 4, 2022

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.