Web-based Expert Bots System in Identifying Complementary Personality Traits and Recommending Optimal Team Composition

The use of web-based expert systems in the workplace has become increasingly common in recent years, with companies using these automated tools to streamline a range of tasks, from customer service to employee training. However, the potential of web-based expert bots systems to help build more effective teams by identifying employees with complementary personality traits and providing recommendations for team composition has received less attention. This paper investigates the application of a web-based expert bots’ system in identifying complementary personality traits among employees to recommend optimal team compositions. We developed a web-based expert bot system, augmented by a chatbot interface, to evaluate and synthesize employee personality profiles for improved team alignment. The results, derived from questionnaire feedback and prototype assessments, demonstrate the system's capability to enhance team performance metrics and behavioral competencies. The discussion outlines the system's advantages, and its potential in organizational settings, and acknowledges its limitations. Web-based expert systems with chatbots that exhibit unique personalities tend to be more engaging and effective. Consequently, this system is expected to not only foster better team cohesion but also to increase user involvement and satisfaction. Future work is dedicated to expanding the system's capabilities and conducting extensive field testing to establish its practical effectiveness.

@article{Fatani2024,
  title     = {Web-based Expert Bots System in Identifying Complementary Personality Traits and Recommending Optimal Team Composition},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {15},
  number    = {2},
  year      = {2024},
  publisher = {The Science and Information Organization},
  author    = {Mysaa Fatani and Haneen Banjar},
  doi       = {10.14569/IJACSA.2024.0150213},
  url       = {https://doi.org/10.14569/IJACSA.2024.0150213}
}