ETRO VUB
About ETRO  |  News  |  Events  |  Vacancies  |  Contact  
Home Research Education Industry Publications About ETRO

Master theses

Current and past ideas and concepts for Master Theses.

Body Language Detection for Personality Assessment

Subject

Automatic personality- and behaviour analysis related to job interviews is a recent field that has caught increasing interest from academics and business life. Current research is mainly focused on the Big Five personality dimensions (Openness, Conscientiousness, Extraversion, Agreeableness and Neuroticism) and measurements are usually limited to facial expressions, head movements and non-verbal speech features.
This thesis is part of a collaboration project, between ETRO-AVSP and Facelytix NV, for personality assessment in job interviews through video interviews. In this research project, we focus on a full non-verbal behaviour detection system, relating it to an extended version of the Big Five theory, where we investigate the correlation of non-verbal behaviours to 30 personality traits.
This thesis work will focus on detecting body language (e.g. the amount of hand movement, placement of the hands on the face, body posture, and shoulder movements), and the analysis of these features in relation to the 30 personality traits.

Kind of work

The proposed research is focused on automatic detection of body language performed in a video interview setting. In addition, an analysis is required to relate the detected body language to the personality of the interviewee. The student will (i) assist in data acquisition in collaboration with Facelytix NV, (ii) formulate the body language detection problem in relation to personality assessment of the interviewee and annotate the videos with the necessary labels, and (iii) build a body language detection system and analyse the relation to personality.

Framework of the Thesis

• D. Frauendorfer, M. Schmid Mast. The Impact of Nonverbal Behavior in the Job Interview. The Social Psychology of Nonverbal Communication, pp 220-247, 2015 https://link.springer.com/chapter/10.1057/9781137345868_11
• A. Vinciarelli and G. Mohammadi, "A Survey of Personality Computing," in IEEE Transactions on Affective Computing, vol. 5, no. 3, pp. 273-291, July-Sept. 1 2014. http://people.ict.usc.edu/~gratch/CSCI534/Readings/persosurvey.pdf
• A. Subramaniam, V. Patel, et al., “Bi-modal First Impressions Recognition Using Temporally Ordered Deep Audio and Stochastic Visual Features”. Computer Vision – ECCV 2016 Workshops, pp. 337 – 348, 2016. https://arxiv.org/abs/1610.10048
• Shan Lu, G. Tsechpenakis, D. N. Metaxas, M. L. Jensen and J. Kruse, "Blob Analysis of the Head and Hands: A Method for Deception Detection," Proc. of the 38th Annual Hawaii International Conference on System Sciences, Big Island, HI, USA, 2005, pp. 20c-20c. https://pdfs.semanticscholar.org/6ba6/f00897734afd0500bf3400128c3dfd13da58.pdf

In collaboration with Dr. Isabel Gonzalez (Facelytix NV) isabel.gonzalez@facelytix.com

Expected Student Profile

• Following an MSc in a field related to one or more of the following: electrical engineering, computer science, applied mathematics
• Experience with image processing and signal processing.
• Experience with machine learning and statistics.
• Strong programming skills (MATLAB, Python, …).
• Interest in performing human-human/human-machine experiments
• Ability to write scientific reports and communicate research results at conferences in English.

Promotor

Prof. Hichem Sahli

+32 (0)2 629 2916

hsahli@etrovub.be

more info

Supervisor

Dr. Meshia Oveneke

+32 (0)2 629 2969

mcovenek@etrovub.be

more info

- Contact person

- IRIS

- AVSP

- LAMI

- Contact person

- Thesis proposals

- ETRO Courses

- Contact person

- Spin-offs

- Know How

- Journals

- Conferences

- Books

- Vacancies

- News

- Events

- Press

Contact

ETRO Department

info@etro.vub.ac.be

Tel: +32 2 629 29 30

©2019 • Vrije Universiteit Brussel • ETRO Dept. • Pleinlaan 2 • 1050 Brussels • Tel: +32 2 629 2930 (secretariat) • Fax: +32 2 629 2883 • WebmasterDisclaimer