Detecting uncertainty in spoken dialogues: an explorative research to the automatic detection of a speakers' uncertainty by using prosodic markers


Share/Save/Bookmark

Dral, J. and Heylen, D.K.J. and Akker, H.J.A. op den (2008) Detecting uncertainty in spoken dialogues: an explorative research to the automatic detection of a speakers' uncertainty by using prosodic markers. In: Sentiment analysis: emotion, metaphor, ontology and terminology, 27 May 2008, Marrakech, Marocco (pp. pp. 72-78).

open access
[img] PDF
117kB
Abstract:This paper reports results in automatic detection of speakers uncertainty in spoken dialogues by using prosodic markers. For
this purpose a substantial part of the AMI corpus (a multi-modal multi-party meeting corpus) has been selected and converted
to a suitable format so its data could be analyzed for selected prosodic features. In the absence of relevant stance annotations
on (un)certainty, lexical markers (hedges) have been used to mark utterances as either certain, or uncertain. Results show that
prosodic features can indeed be used to detect speaker uncertainty in spoken dialogues. The classifiers can distinguish
uncertain from neutral utterances with an accuracy of 75% which is 25% over the baseline.
Item Type:Conference or Workshop Item
Faculty:
Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:
Link to this item:http://purl.utwente.nl/publications/65341
Official URL:http://www.lrec-conf.org/proceedings/lrec2008/workshops/W6_Proceedings.pdf
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page

Metis ID: 255453