Neural Network-based exploration of construct validity for Russian version of the 10-item Big Five Inventory
Anastasia Sergeeva, Bogdan Kirillov, Alyona Dzhumagulova

TL;DR
This paper introduces a neural network-based method to assess construct validity of questionnaires, demonstrated on the Russian TIPI, offering a quick and versatile alternative to traditional path models especially for large-scale and intercultural studies.
Contribution
It presents a novel neural network approach for evaluating construct validity, specifically applied to the Russian version of the TIPI, enhancing efficiency and applicability in large and intercultural surveys.
Findings
Neural network method effectively assesses construct validity.
TIPI-RU shows good convergent validity with neural network analysis.
Method offers a convenient substitute for traditional path models.
Abstract
This study aims to present a new method of exploring construct validity of questionnaires based on neural network. Using this test we further explore convergent validity for Russian adaptation of TIPI (Ten-Item Personality Inventory by Gosling, Rentfrow, and Swann). Due to small number of questions TIPI-RU can be used as an express-method for surveying large number of people, especially in the Internet-studies. It can be also used with other translations of the same questionnaire in the intercultural studies. The neural network test for construct validity can be used as more convenient substitute for path model.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
