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

J. Dral, Dirk K.J. Heylen, Hendrikus J.A. op den Akker

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    41 Downloads (Pure)

    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.
    Original languageUndefined
    Title of host publicationSentiment analysis: emotion, metaphor, ontology and terminology
    EditorsK. Ahmad
    Place of PublicationParis
    PublisherELRA
    Pages72-78
    Number of pages7
    ISBN (Print)2-9517408-4-0
    Publication statusPublished - 2008

    Publication series

    Name
    PublisherELRA
    Number412

    Keywords

    • HMI-MI: MULTIMODAL INTERACTIONS
    • METIS-255453
    • IR-65341
    • EWI-14955

    Cite this

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