Sotarat ThammaboosadeeMahidol University2018-11-092018-11-092014-01-012014 9th International Conference on Digital Information Management, ICDIM 2014. (2014), 11-152-s2.0-84930422740https://repository.li.mahidol.ac.th/handle/20.500.14594/33718© 2014 IEEE. This paper proposes an identifying methodology of the relevant criminal offences charges, given textual information of the criminal cases in the Civil Law system. The model is devised as a multi-stage based on the criminal law codes. The first stage is to identify action types, using modular classifier. The modularity is designed based on the offences charges, which were abstractly categorized by elements of crimes in criminal codes. The second stage is to identify the legal elements, leading to general provisions. This classification stage is designed as independent multi-classifiers. The input data is preprocessed from text to features by some natural language processing methods. The integrated model aims at achieving high accuracy of classification while reserving explainable results, which is required in an application of legal domain.Mahidol UniversityComputer ScienceDecision SciencesAn elements-based multi-stage charges identification model for textual criminal casesConference PaperSCOPUS10.1109/ICDIM.2014.6991415