Show simple item record

dc.contributor.author
Märkle-Huß, Joscha
dc.contributor.author
Feuerriegel, Stefan
dc.contributor.author
Prendinger, Helmut
dc.date.accessioned
2017-11-13T16:36:07Z
dc.date.available
2017-08-31T21:59:52Z
dc.date.available
2017-09-05T15:14:55Z
dc.date.available
2017-11-13T16:36:07Z
dc.date.issued
2017
dc.identifier.isbn
9780998133102
en_US
dc.identifier.other
10.24251/hicss.2017.135
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/182422
dc.identifier.doi
10.3929/ethz-b-000182422
dc.description.abstract
Conventional sentiment analysis usually neglects semantic information between (sub-)clauses, as it merely implements so-called bag-of-words approaches, where the sentiment of individual words is aggregated independently of the document structure. Instead, we advance sentiment analysis by the use of rhetoric structure theory (RST), which provides a hierarchical representation of texts at document level. For this purpose, texts are split into elementary discourse units (EDU). These EDUs span a hierarchical structure in the form of a binary tree, where the branches are labeled according to their semantic discourse. Accordingly, this paper proposes a novel combination of weighting and grid search to aggregate sentiment scores from the RST tree, as well as feature engineering for machine learning. We apply our algorithms to the especially hard task of predicting stock returns subsequent to financial disclosures. As a result, machine learning improves the balanced accuracy by 8.6 percent compared to the baseline
en_US
dc.language.iso
en
en_US
dc.publisher
HICSS
en_US
dc.rights.uri
http://creativecommons.org/licenses/by-nd/4.0/
dc.subject
Sentiment analysis
en_US
dc.subject
Semantic Relationships
en_US
dc.subject
Rhetoric structure theory
en_US
dc.subject
Machine learning
en_US
dc.title
Improving sentiment analysis with document-level semantic relationships from rhetoric discourse structures
en_US
dc.type
Conference Paper
dc.rights.license
Creative Commons Attribution-NoDerivatives 4.0 International
ethz.book.title
Proceedings of the 50th Hawaii International Conference on System Sciences
en_US
ethz.pages.start
1142
en_US
ethz.pages.end
1151
en_US
ethz.version.deposit
publishedVersion
en_US
ethz.event
50th Hawaii International Conference on System Sciences (HICSS)
en_US
ethz.event.location
Waikoloa Village, HI, USA
en_US
ethz.event.date
January 4-7, 2017
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02120 - Dep. Management, Technologie und Ökon. / Dep. of Management, Technology, and Ec.::09623 - Feuerriegel, Stefan / Feuerriegel, Stefan
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02120 - Dep. Management, Technologie und Ökon. / Dep. of Management, Technology, and Ec.::09623 - Feuerriegel, Stefan / Feuerriegel, Stefan
en_US
ethz.date.deposited
2017-08-31T21:59:53Z
ethz.source
FORM
ethz.eth
no
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2017-09-05T15:14:57Z
ethz.rosetta.lastUpdated
2017-11-13T16:36:22Z
ethz.rosetta.exportRequired
true
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Improving%20sentiment%20analysis%20with%20document-level%20semantic%20relationships%20from%20rhetoric%20discourse%20structures&rft.date=2017&rft.spage=1142&rft.epage=1151&rft.au=M%C3%A4rkle-Hu%C3%9F,%20Joscha&Feuerriegel,%20Stefan&Prendinger,%20Helmut&rft.isbn=9780998133102&rft.genre=proceeding&rft_id=info:doi/9780998133102&rft.btitle=Proceedings%20of%20the%2050th%20Hawaii%20International%20Conference%20on%20System%20Sciences
 Search via SFX

Files in this item

Thumbnail

Publication type

Show simple item record