[Paper Review] MentalGame: Predicting Personality-Job Fitness for Software Developers Using Multi-Genre Games and Machine Learning Approaches

Soroush Elyasi, Arya VarastehNezhad+1 more|arXiv (Cornell University)|Jan 3, 2026

Educational Games and Gamification0 citations

TL;DR

The paper proposes a game-based framework that uses multi-genre serious games and machine learning to predict software-developer suitability from gameplay-derived behavioral features, achieving up to 97% precision and 94% accuracy.

ABSTRACT

Personality assessment in career guidance and personnel selection traditionally relies on self-report questionnaires, which are susceptible to response bias, fatigue, and intentional distortion. Game-based assessment offers a promising alternative by capturing implicit behavioral signals during gameplay. This study proposes a multi-genre serious-game framework combined with machine-learning techniques to predict suitability for software development roles. Developer-relevant personality and behavioral traits were identified through a systematic literature review and an empirical study of professional software engineers. A custom mobile game was designed to elicit behaviors related to problem solving, planning, adaptability, persistence, time management, and information seeking. Fine-grained gameplay event data were collected and analyzed using a two-phase modeling strategy where suitability was predicted exclusively from gameplay-derived behavioral features. Results show that our model achieved up to 97% precision and 94% accuracy. Behavioral analysis revealed that proper candidates exhibited distinct gameplay patterns, such as more wins in puzzle-based games, more side challenges, navigating menus more frequently, and exhibiting fewer pauses, retries, and surrender actions. These findings demonstrate that implicit behavioral traces captured during gameplay is promising in predicting software-development suitability without explicit personality testing, supporting serious games as a scalable, engaging, and less biased alternative for career assessment.

Motivation & Objective

• Identify developer-relevant personality and behavioral traits from literature and an empirical study of professionals.
• Design a multi-genre serious game to elicit traits linked to software development.
• Develop a predictive ML model that uses gameplay-derived features to infer suitability for software development.

Proposed method

• Identify MBTI Thinking trait as central to software development, complemented by associated behavioral traits.
• Develop a Unity-based mobile serious game with modular stages across genres to elicit cognitive and behavioral signals.
• Instrument a backend (ASP.NET Core, SQL Server) to log fine-grained gameplay events with consent-based data handling.
• Preprocess high-dimensional gameplay data, select informative features, and apply two-phase modeling to leverage labeled and unlabeled data.
• Use labeled examples of verified software-development specialists to train and evaluate models, with unlabeled data inferred via the predictive framework.

Experimental results

Research questions

• RQ1 Can gameplay-derived behavioral features predict suitability for software development beyond self-reported personality measures?
• RQ2 Which developer-relevant traits and gameplay patterns best distinguish suitable candidates?
• RQ3 Does a two-phase modeling approach (dataset completion then full-scope prediction) improve accuracy using limited labels?
• RQ4 How effective is MBTI Thinking-type and associated behaviors as predictors in a game-based assessment?
• RQ5 What are the practical implications of using game-based assessment for scalable, less biased career guidance?

Key findings

• The model achieved up to 97% precision and 94% accuracy in predicting software-development suitability from gameplay features.
• Distinct gameplay patterns characterized suitable candidates, such as more puzzle-game wins, more side challenges, frequent menu navigation, and fewer pauses, retries, and surrender actions.
• A two-phase modeling strategy enables prediction with limited labeled data by first completing labels with personality-based information and then predicting suitability from gameplay features.
• The approach demonstrates that implicit behavioral traces during gameplay can be a scalable, engaging, and less biased alternative to explicit personality testing for career assessment.