Fact sheet: Automatic Self-Reported Personality Recognition Track
This work addresses the challenge of understanding contextual influences in personality recognition for researchers, but it is incremental as it focuses on baseline development rather than a new method.
The paper tackled the problem of disentangling contextual factors in automatic self-reported personality recognition by developing an informed baseline model using only metadata features like age, gender, and number of sessions, which achieved superior or similar performance compared to state-of-the-art models based on audio, linguistic, or visual features.
We propose an informed baseline to help disentangle the various contextual factors of influence in this type of case studies. For this purpose, we analysed the correlation between the given metadata and the self-assigned personality trait scores and developed a model based solely on this information. Further, we compared the performance of this informed baseline with models based on state-of-the-art visual, linguistic and audio features. For the present dataset, a model trained solely on simple metadata features (age, gender and number of sessions) proved to have superior or similar performance when compared with simple audio, linguistic or visual features-based systems.