The Automatic Analysis of Emotion in Political Speech Based on Transcripts.
Automatic sentiment analysis is used extensively in political science. The digitization of legislative transcripts has increased the potential application of established tools for the automated analyses of emotion in text. Unlike in writing, however, expressing emotion in speech involves intonation,...
| Publicado en: | Political Communication Vol. 39; no. 1; pp. 98 - 122 |
|---|---|
| Autores principales: | , , , , , |
| Formato: | Artículo |
| Publicado: |
Taylor & Francis Ltd
2022
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=155184364&site=ehost-live header: @attributes: shortDbName: ssf uiTerm: 155184364 longDbName: Social Sciences Full Text (H.W. Wilson) uiTag: AN controlInfo: bkinfo: jinfo: jid: 10584609 POU jtl: Political Communication issn: 10584609 maglogo: Y pubinfo: dt: 2022 vid: 39 iid: 1 pid: 377 pub: Taylor & Francis Ltd artinfo: ui: 155184364 10.1080/10584609.2021.1952497 ppf: 98 ppct: 24 formats: tig: atl: The Automatic Analysis of Emotion in Political Speech Based on Transcripts. aug: au: Cochrane, Christopher Rheault, Ludovic Godbout, Jean-François Whyte, Tanya Wong, Michael W.-C. Borwein, Sophie affil: Department of Political Science, University of Toronto, Toronto, Ontario, Canada Department of Political Science, Université de Montréal, Quebec, Canada su: Sentiment analysis Political science Intonation (Phonetics) Facial expression Body language Emotions & politics Political oratory sug: subj: Sentiment analysis Political science Intonation (Phonetics) Facial expression Body language Emotions & politics Political oratory keyword: legislatures sentiment analysis Text-as-data word embeddings legislatures sentiment analysis Text-as-data word embeddings ab: Automatic sentiment analysis is used extensively in political science. The digitization of legislative transcripts has increased the potential application of established tools for the automated analyses of emotion in text. Unlike in writing, however, expressing emotion in speech involves intonation, facial expressions, and body language. Drawing on a new dataset of annotated texts and videos from the Canadian House of Commons, this paper does three things. First, we examine whether transcripts capture the emotional content of speeches. We find that transcripts capture sentiment, but not emotional arousal. Second, we compare strategies for the automated analysis of sentiment in text. We find that leading approaches performed reasonably well, but sentiment dictionaries generated using word embeddings surpassed these other approaches. Finally, we test the robustness of the approach based on word embeddings. Although the methodology is reasonably robust to alternative specifications, we find that dictionaries created using word embeddings are sensitive to the choice of seed words and to training corpus size. We conclude by discussing the implications for analyses of political speech. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: N holdings: @attributes: islocal: N |
|---|