Inferring stance in news broadcasts from prosodic-feature configurations. (July 2018)

• Record Type: Journal Article
• Authors: Ward, Nigel G.; Carlson, Jason C.; Fuentes, Olac
• Is Part Of: Computer speech & language. Volume 50(2018)
• Page Start: 85
• Page End: 104
• Publication Date: 2018-07
• Subjects: Information retrieval -- Attitude -- Broadcast news -- Prosody -- American English -- Mandarin -- Turkish; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2017.12.007
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: A description of 14 aspects of stance, extending the inventory of computationally modeled aspects of sentiment and attitude. The finding that stance is commonly present in news stories. A model of how prosody conveys stance. A demonstration that this model is able to infer stance, in three unrelated languages. Evidence that the prosodic expressions of stance include configurations of diverse prosodic features Illustrations of such configurations. The finding that the significance of a prosodic-feature configuration can depend on where it occurs in a story. The finding that the prosodic expressions of stance are extremely language-dependent. Abstract: Speech conveys many things beyond content, including aspects of appraisal, feeling, and attitude that have not been much studied. In this work, we identify 14 aspects of stance that occur frequently in radio news stories and that could be useful for information retrieval, including indications of subjectivity, immediacy, local relevance, and newness. We observe that newsreaders often mark their stance with prosody. To model this, we treat each news story as a collection of overlapping 6-s patches, each of which may convey one or more aspects of stance by its prosody. The stance of a story is then estimated from the information in its patches. Experiments with English, Mandarin, and Turkish show that this technique enables automatic identification of many aspects of stance in news broadcasts.