close

PhD position Machine learning for Human Behaviors in Negotiations and Deliberations

Research / Academic
Delft

Negotiations and deliberations involve understanding and managing interpersonal dynamics, relationships, motivations, and navigating conflicts. While there has been much existing research in building negotiating agents, there remains a gap to integrate situated understanding of human behaviors and how these could affect negotiation and deliberation outcomes. What could be perceived from people’s interaction and communication patterns as well as decision-making across the negotiation and deliberation process? One solution is to leverage information gathered pre- and post- interaction, as well as multimodal data during the interaction process. As a member of this project, you will do research in the pipeline of multimodal machine perception and decision-making from data collection, annotation, algorithm and model design, to evaluation. The team you would join is a multi-disciplinary team, in which everyone is encouraged to take initiatives and progress in the work is achieved by shared ownership.
This project is part of a larger Groeifond consortium (Oncode Accelerator) which focuses on drug development and cancer research. This project is part of a work package that researches negotiations and deliberations between stakeholders in research and potentially clinical settings. This project aims to develop novel frameworks and learning approaches that integrate human behavior modeling to support decision-making in real-life scenarios.
The successful applicant will develop computational methods to model human behaviors using multimodal data - video and audio (e.g., speech and paralinguistics data), and to generate insights and feedback for descision-making, specifically for negotiation and deliberations in real-life situated settings.
The candidate will be embedded within the larger Interactive Intelligence Group at the Intelligent Systems Department at the TU Delft Electrical Engineering, Mathematics, and Computer Science faculty. For information about PhD at TU Delft, please visit https://www.tudelft.nl/onderwijs/opleidingen/phd

Requirements:

We are looking for applicants who have or expect to receive a Master's degree before joining the project. Relevant topics include multimodal machine learning, affective computing, natural language processing, and reinforcement learning. Experience in some of the related fields is preferred: audio and speech processing, computer vision, machine learning, and pattern recognition. As this project is interdisciplinary, having general interests and affinity in human-computer interaction, social science, and psychology is recommended. 
Doing a PhD at TU Delft requires English proficiency at a certain level to ensure that the candidate is able to communicate and interact well, participate in English-taught Doctoral Education courses, and write scientific articles and a final thesis. For more details please check the Graduate Schools Admission Requirements.

Salary Benefits:

Doctoral candidates will be offered a 4-year period of employment in principle, but in the form of 2 employment contracts. An initial 1,5 year contract with an official go/no go progress assessment within 15 months. Followed by an additional contract for the remaining 2,5 years assuming everything goes well and performance requirements are met.
Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities, increasing from € 2872 per month in the first year to € 3670 in the fourth year. As a PhD candidate you will be enrolled in the TU Delft Graduate School. The TU Delft Graduate School provides an inspiring research environment with an excellent team of supervisors, academic staff and a mentor. The Doctoral Education Programme is aimed at developing your transferable, discipline-related and research skills.
The TU Delft offers a customisable compensation package, discounts on health insurance, and a monthly work costs contribution. Flexible work schedules can be arranged.
For international applicants, TU Delft has the Coming to Delft Service. This service provides information for new international employees to help you prepare the relocation and to settle in the Netherlands. The Coming to Delft Service offers a Dual Career Programme for partners and they organise events to expand your (social) network.

Work Hours:

36 - 40 hours per week

Address:

Mekelweg 2