A Multimodal Approach to Confidence, Emotion and Personality Assessment in Virtual Interviews
Boletim da Sociedade Paranaense de Matemática · 19.06.2026 · 44 (17) · 1-21
DOI: 10.5269/bspm.82391 ↗Kurz gefasst
Fachartikel in der Zeitschrift Boletim da Sociedade Paranaense de Matemática, online erschienen am 19.06.2026. Verfasst von Baby Vadlana und 3 weiteren Autor:innen. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The recruitment landscape emphasizes prioritizing candidate s technical skills over interpersonal skills such as emotional intelligence, suitable behaviour, communication style and adaptability. Traditional systems analyse text or skill based responses , thereby missing out to analyse behaviour and real time emotions in interview. This creates gap in analysing the candidate s true personality profile and style of interaction. Therefore, there is necessity of multimodal system to evaluate , what candidate speak, how they speak and how they present themselves during interview. To address this limitations, this study proposes a multimodal emotion recognition system which strengthens for personality assessment in digital interviews. This framework processes by integrating linguistic cues from textual transcripts, paralinguistic cues from speech signals and visual expressions from video frames. Text based emotion features are extracted using a fine tuned transformer model, achieved 43% accuracy. Audio based emotional cues are recognized using a speech emotion pipeline, achieved 63% accuracy. Facial expressions are analysed using vision based module . Early fusion strategy has been applied to integrate these multiple modalities which enables the system to get consolidated emotional state from the interview. This multimodal architecture gives a great support to evaluate candidate complete profile, which makes the recruitment decision holistic. This makes the organizations to hire the candidates who are not only technically strong but also with good interpersonal skills.
Zitieren
APA
Vadlana, B., Akhil, K., Subhashini, N., & Krishna, M. V. (2026). A Multimodal Approach to Confidence, Emotion and Personality Assessment in Virtual Interviews. Boletim da Sociedade Paranaense de Matemática, 44(17), 1-21. https://doi.org/10.5269/bspm.82391
Vancouver
Vadlana B, Akhil K, Subhashini N, Krishna MV. A Multimodal Approach to Confidence, Emotion and Personality Assessment in Virtual Interviews. Boletim da Sociedade Paranaense de Matemática. 2026;44(17):1-21. doi:10.5269/bspm.82391
BibTeX
@article{Vadlana2026,
author = {Vadlana, Baby and Akhil, Karnam and Subhashini, Nallanagula and Krishna, Mallupeddi Vamsi},
title = {A Multimodal Approach to Confidence, Emotion and Personality Assessment in Virtual Interviews},
journal = {Boletim da Sociedade Paranaense de Matemática},
year = {2026},
volume = {44},
number = {17},
pages = {1--21},
doi = {10.5269/bspm.82391}
}
EUVIMED