Where Vocational Counsellors Are Scarce, Universidad Técnica de Machala Builds a DeepSeek-Powered Career-Guidance Chatbot for Ecuadorian Students

Ecuador's secondary schools face a shortage of trained vocational-guidance counsellors and limited access to guidance technology, leaving many final-year students to choose a university career path with little structured support.
Researchers at Universidad Técnica de Machala (UTMACH) built a chatbot powered by the DeepSeek language model, using prompt-engineering techniques to interpret students' open-ended answers and assess their competencies, then match them to a suggested academic path drawn from UTMACH's own programme offerings.
The team evaluated it with a quasi-experimental design combining a single treatment group and a control group, involving 351 third-year secondary students across participating Ecuadorian schools. Students completed the government's official SENESCYT vocational aptitude test, then interacted with the AI chatbot, then completed a Likert-scale perception survey. The chatbot's suggestions matched the SENESCYT test results in 80.1% of cases, and 76% of students rated the conversational interaction, question clarity and relevance of recommendations positively; the study was published in the peer-reviewed journal Informática y Sistemas (Universidad Técnica de Manabí, November 2025).
The 80.1% concordance is a meaningful validation against an external government benchmark rather than self-report alone, but it also means roughly one in five recommendations diverged from the official test, and the chatbot's suggested pathways were drawn specifically from UTMACH's own course catalogue, so a student's options were implicitly shaped by one university's offerings rather than the full national landscape — a caveat prospective adopters elsewhere should weigh before reusing the tool unmodified.

Read the full analysis: https://revistas.utm.edu.ec/index.php/Informaticaysistemas/article/view/7907