Date published:

ComPathos: computational model of pathos for modern rhetoric

Location: Faculty of Psychology and Cognitive Sciences: Reasoning Research Lab (or remote).

Duration: 6-12 months

Working language: English

Position description:

ComPathos project aims at providing new means for understanding how emotions expressed by (or appealed to) by speakers in persuasive dialogues are influencing the emotions of hearers. The trainee will focus on constructing computational models of arguments from natural language, using the material from English-language political debate. The analysis will focus on the role of emotions in argumentation. The trainee will work under the direct supervision of dr Barbara Konat, who specialises in natural language argumentation and sentiment analysis. The trainee  be invited to the preparation an academic journal publication to which they will contribute during the internship.

The activities will include:

- Argument analysis in textual data from English language media sources (annotation).

- Natural Language Processing of English language data (including automated argument analysis, sentiment analysis and applications of neural networks for argument mining). The scope and advancement level will be adjusted to the Trainee’s skills and interests.

- Literature review, data analysis, preparation of reports.

Required qualification

- English at min C1 level

- experience in annotation or Python programming skills are welcome