Unconstitutionality Prevention in Bills Using Hybrid AI

One of the most important legal assessments during legislative drafting proposals in Parliament is to check whether the bills have some provisions clashing with the Constitutional norms. Sometimes this situation is intentionally created by the proposer of a party to underline inconsistencies or incompleteness in the legal systems according to the reality of the society, but frequently, they are mistakes to avoid. This paper presents a method to calculate a multi-factor index of presumption of unconstitutionality of the provisions of a bill, to inform the proponent concerning a possible constitutional conflict. The paper uses a large dataset of bills, coming from the Chamber of Deputies of Italy, combined with Constitutional Court judgments and abstracts, EU and National legislation (9095 Italian laws, 3710 bills, 2979 judgments from the Constitutional Court). The methodology used is hybrid, considering different technological components, linked in a pipeline: i) embedding similarity; ii) normative references navigation; iii) semantic topic of the bill; iv) legislation cited in the judgments score based on the abrogated.