Automation of Processes of Anti-corruption and Law Expertise of Draft Regulations

Student: Portnova Olga

Supervisor: Dmitry A. Romanov

Educational Programme: Business Informatics (Master)

Year of Graduation: 2017

Key words: Anti-corruption examination, corruption factor, lexical pattern, АОТ, NLP, text analysis, natural language processing, expert system, machine learning. Subject of this graduation paper is a process of automating the conduct of anti-corruption expertise of draft laws. The proposed approach is application of an hybrid expert system based on a combination of expert work and a base of lexical-syntactic patterns. The goal of this work is to analyze a behavior of a system with different ways of human participation in the formation of corruption-related factor base. This paper also provides an overview of existing approaches of resolving text analysis problems. The result is a series of experiments to assess the effectiveness of the hybrid expert system application. Further work can be aimed at finding the optimal combination of experts crowdsourcing and methods of machine learning in the form of self-learning system of rules. This work is structured as follows: the first chapter is dedicated to an overview of existing methods of intellectual textual data analysis, the second chapter details the method of using lexico-syntactic patterns to identify corruption-related factors in legal documents, the third chapter is dedicated to conducting experiments with lexico-syntactic patterns base in Anticor expert system.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses