Personality and general questionnaire processing methods for various experiments.
- BFI-2
- VAS-F
Questionnaire answers are...
- read via command line interface
- ints in a numpy ndarray (.npy)
- ints in a csv file (.csv)
- strings in a csv file (.csv)
For BFI-2, the OCEAN and FACET values are scaled to the range [0..1] per participant.
For VAS-F, the relative values are calculated.
pip install personality_questionnaire
git clone https://github.com/fodorad/personality_questionnaire
cd personality_questionnaire
pip install .
pip install -U -r requirements.txt
python -m unittest discover -s test
If you installed it via pip:
personality_questionnaire --participant_id test --questionnaire bfi2
alternative call:
python personality_questionnaire/api.py --participant_id test --questionnaire bfi2
If you installed it via pip:
personality_questionnaire --participant_id test --questionnaire vasf --vasf_tag pre
personality_questionnaire --participant_id test --questionnaire vasf --vasf_tag post
alternative call:
python personality_questionnaire/api.py --participant_id test --questionnaire vasf --vasf_tag pre
python personality_questionnaire/api.py --participant_id test --questionnaire vasf --vasf_tag post
LinMulT is trained for Big Five personality trait estimation using the First Impressions V2 dataset and sentiment estimation using the MOSI and MOSEI datasets.
- paper: Multimodal Sentiment and Personality Perception Under Speech: A Comparison of Transformer-based Architectures (pdf, website)
- code: https://github.com/fodorad/PersonalityLinMulT
- Add support for the following questionnaires: HEXACO
- 1.1.0: Add support for VAS-F and interactive CMD interface.
- 1.0.0: Add support for BFI-2 and PyPI publish.
- Ádám Fodor (foauaai@inf.elte.hu)