Publication: An elements-based multi-stage charges identification model for textual criminal cases
Issued Date
2014-01-01
Resource Type
Other identifier(s)
2-s2.0-84930422740
Rights
Mahidol University
Rights Holder(s)
SCOPUS
Bibliographic Citation
2014 9th International Conference on Digital Information Management, ICDIM 2014. (2014), 11-15
Suggested Citation
Sotarat Thammaboosadee An elements-based multi-stage charges identification model for textual criminal cases. 2014 9th International Conference on Digital Information Management, ICDIM 2014. (2014), 11-15. doi:10.1109/ICDIM.2014.6991415 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/33718
Research Projects
Organizational Units
Authors
Journal Issue
Thesis
Title
An elements-based multi-stage charges identification model for textual criminal cases
Author(s)
Other Contributor(s)
Abstract
© 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.