Kairos Career Dataset

This dataset was developed as part of the Kairos research project, an AI-based career guidance virtual assistant built upon natural language processing, machine learning, and Holland's RIASEC model. It supports the development, training, and evaluation of the system described in the associated research article and consists of two main resources: a corpus of 1,500 Spanish-language sentences annotated according to the six RIASEC dimensions (Realistic, Investigative, Artistic, Social, Enterprising, and Conventional), and a database of 60 undergraduate academic programs classified using three-letter RIASEC profile codes. This dataset can be used for research on vocational profile classification, natural language processing model training and evaluation, career recommendation systems, and AI-based career guidance applications in Spanish. It is publicly released to promote research reproducibility and facilitate future studies in this field.