Advanced Variable Tuning and Biases in Chatbot Models: Analysis of the PT AH Prototype

Current research in the field of chatterbots lacks detailed information on the evolution of prototypes after the startup, where the system exploitation reveals engine performance and biases. This paper presents the tuning and evolution of PTAH, an AI system that interacts in natural language using a precise combination of linguistic processing tools. This analysis aims to introduce not only a methodology but also to show and compare how certain parameterization considerations impact on the results despite the sophistication of algorithmic. Results allow to affirm that the post-deployment treatment is critical for the correct parameterization of NLP systems using AI approaches, due the bias and entropy speed required to feed the intelligent learning of the optimized model in chatter contexts.