Modeling, Recognizing, and Explaining Apparent Personality From Videos

Explainability and interpretability are two critical aspects of decision support systems. Despite their importance, it is only recently that researchers are starting to explore these aspects. This paper provides an introduction to explainability and interpretability in the context of apparent personality recognition. To the best of our knowledge, this is the first effort in this direction. We describe a challenge we organized on explainability in first impressions analysis from video. We analyze in detail the newly introduced data set, evaluation protocol, proposed solutions and summarize the results of the challenge. We investigate the issue of bias in detail. Finally, derived from our study, we outline research opportunities that we foresee will be relevant in this area in the near future.

Automated summary

Explainability and interpretability are essential aspects of decision support systems, and researchers are starting to explore their importance. This paper introduces the concept of explainability and interpretability within the context of apparent personality recognition. The authors describe a challenge they organized on explainability in first impressions analysis from video, analyzing the dataset, evaluation protocol, proposed solutions, and summarizing the results. The issue of bias is also investigated, and the study outlines future research opportunities in this area.