Naslov
A multimodal approach to detection of faking in a selection interview

Autori
Parmač Kovačić, Maja ; Juničić, Nataša

Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, sažetak, znanstveni

Izvornik
EAWOP Congress The future is now: the changing world of work - Book of abstracts / - Katovice, 2023, 925-926

Skup
21st EAWOP Congress

Mjesto i datum
Katowice, Poljska, 24.05.2023. - 27.05.2023

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
selection interview ; faking ; behavioral cues

Sažetak
Research goals and why the work was worth doing The selection interview is one of the most frequently used methods of personnel assessment for various jobs, despite its susceptibility to response distortion. Existing research indicates that experts in personnel selection are no better than chance in their detection of response distortion, irrespective of an interviewing experience. Some authors have proposed investigating the behavioural indicators of faking during the interview as one of the potential solutions for this challenge. However, the existing research on this topic is still scarce. Therefore, the aim of this study was to explore the possibility of detection of faking in a selection interview through a multimodal approach, based on paraverbal, verbal and nonverbal cues and facial expressions. Additionally, it was examined whether it is possible to detect response distortion with two different algorithms: one based on logistic regression and the other on artificial neural networks. Theoretical background According to various authors, differences in behavioural cues should mirror the differences in psychological processes between honesty and deception. More precisely, according to some theories (i.e., Buller &amp ; Burgoon, 1996 ; DePaulo et al, 2003 ; Walczyk et al, 2014 ; Ekman, 2002), deception should, at least under some circumstances, be more cognitively taxing, accompanied by more rigid behaviour and by less authentic facial expressions. Design/Methodology/Approach/Intervention In total, a convenience sample of 102 students/recent graduates (71% female, M age =24.2, SD age =3.08) participated in a videorecorded mock structured selection interview for the position of call centre manager. The interview consisted of two randomly ordered blocks: in one block participants had to answer honestly, while in another their task was to present themselves as an ideal candidate for the position. As an incentive to distort their answers effectively, participants were told that 10% of those with the most convincing self-presentations in faking condition would receive an award coupon of approximately 70 euros. At the end of the interview, some control variables and variables related to the experimental manipulation check were measured. Two independent coders analysed cues from every behavioural category. Additionally, facial expressions were analysed with the OpenFace application. Results obtained The manipulation check indicated that participants answered less honestly, used more faking strategies, experienced more cognitive load and fear of detection, and controlled their behaviour more when presenting themselves as ideal candidates. They achieved higher scores on extraversion and honesty/humility while faking as well. Interestingly, participants reported higher levels of motivation to present themselves convincingly in the honest condition. Regarding the differences in behavioural cues between honest vs. ideal candidate conditions, significant multivariate effects were obtained for paraverbal, verbal and facial expressions (both for human coders and OpenFace) categories. Same levels of performance in classifying interview conditions were achieved both with logistic regression and artificial neural networks, with 65% overall accuracy rates. Limitations Although statistically large effect sizes were obtained for various measures of the experimental manipulation, in an absolute and practical sense the psychological differences between conditions could have been more pronounced. Also, the convenience sample of highly educated participants was used. Conclusions – research and or practical implications/Originality/Value Although it was demonstrated in this study that response distortion in selection interview could be detected by its unique behavioural signature, not all modalities and their cues are equally useful. Additionally, when investigating different algorithms, future researchers should remember that more powerful models are not necessarily more successful in classifying candidate responses during the interview. Relevance to the Congress Theme This study demonstrates the possibilities of an interdisciplinary approach in solving the longstanding problem of faking in selection interviews by combining psychological insights and research design expertise with statistical algorithms and applications based on machine learning and AI. Keywords: Selection interview, faking, behavioural cues

Izvorni jezik
Engleski

Znanstvena područja
Psihologija

POVEZANOST RADA