Cross-disciplinary PhD fellowship in linguistics and computer science at Aix-Marseille University, in France.
Keywords: Language, Social Interaction, Machine Learning
This PhD thesis subject aims at understanding how inter‐individual relationships are established, managed and evolve during conversations. The work aims at extending the notion of interactional profiles (“leader”, “follower”…) in terms of social roles and dynamic patterns such as convergence or divergence. This project proposes to use data science on large spoken conversational data sets in multiple languages (English, French and Mandarin), as well as task-focused real-life conversation from call centers to identify the linguistic traces of interpersonal relationships and their dynamics. Tools from machine learning and natural language processing will provide methodological knowledge for the scientific exploration of language through big data sets, and allow a fine-grained discovery and prediction of behaviors in novel data.
The PhD is fully funded as part of the DOC2AMU European H2020 COFUND program, including personalized training, travel expenses, and conferences attendance.
Candidates should have a background in linguistics and / or machine learning. A condition for application is that they should not have spent more than 1 year in France during the last 3 years.
Aix Marseille University <http://www.univ-amu.fr/en>, the largest French University, is ideally located on the Mediterranean coast, and only 1h30 away from the Alps.
Deadline: June 24, 2016.
More info and application: http://doc2amu.univ-amu.fr/en/language-underpinnings-of-conversational-interpersonal-dynamics- lucid
Feel free to contact us for more information: Laurent Prévot: laurent.prevot at univ-amu.fr www.lpl-aix.fr/person/*prevot* <http://www.lpl-aix.fr/person/prevot> Benoît Favre: benoit.favre at univ-amu.fr pageperso.lif.univ-mrs.fr/~*benoit*.*favre*/ <http://pageperso.lif.univ-mrs.fr/~benoit.favre/> -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 3029 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20160524/db1b7d48/attachment.txt>