Automated value learning from texts: air transportation

Period: 01.01.2017
- 01.01.2020


Assistant professor 

Ph. D.
Olga Zervina
Transport and Management Faculty
Olga Zervina

Academic degree and current position at TSI: Master of Economics, Researcher of the Transport and Management Faculty, Director of Master Professional Program “Aviation Management”, PhD student on Telematics and Logistics Program

Experience – 12 years’ experience in Higher Education (Professional English, Digital Marketing, Career Management), 2 years experience as a Program Director (Aviation Management)

Teaching activity – Business English (Bachelor of Social Sciences in Management); Digital Marketing (Bachelor of Social Sciences in Management); English for Students of Computer Science (Bachelor of Computer Science); Career Management (Bachelor of Social Sciences in Management), English for Students of Logistics (Bachelor of Logistics), etc.

Publication activity – the author of 7 publications, indexed by Scopus and Web of Science

Projects – a national representative and Management Committee Member of COST Action CA19102 “Language In The Human-Machine Era”; member of  the ERASMUS+ KA2 “SPREAD YOUR WINGS” 2017-1-PL01-KA203-038782 project; member of Cost Action: CA18231 Multi3Generation: Multi-task, Multilingual, Multi-modal Language Generation; member of the Cost Action: CA18209 European network for Web-centered linguistic data science. European Social Fund project “Strengthening Transport and Telecommunication Institute Academic Staff in the Areas of Strategic Specialisation” (Specific Objective 8.2.2 “To Strengthen Academic Staff of Higher Education Institutions in the Areas of Strategic Specialisation, 1 year training at Riga International Airport Training Center, Latvia

Supervised theses – Supervisor of 8 Bachelor theses

Research fields/domains – Natural Language Processing, Value Proposition, Start-ups and Innovation Management, Aviation Management, Digital Marketing

Motto – It often seems impossible until it’s done

Project Type: Academic

Main Challenge

Identifying values from texts poses a complex and intricate problem. A data-driven methodology, based on natural language processing, is employed, involving the initial construction of a dataset and subsequent analysis using computational linguistic methods to identify the most effective features and techniques. Furthermore, a corpus linguistic perspective is embraced, underlining the importance of analysing language in its natural context through the use of corpora collected in the field for more reliable language analysis.

Funding: Internal

DA&AI tools:

  • Natural Language Processing
  • Machine Learning


  • Zervina, O., 2023. Value expansion and sense making. Behaviormetrika 50, 585–617.
  • Zervina, O., Stukalina, Y., Pavlyuk, D., 2023. Value Entity Recognition Task in the Air Transportation on the Base of E-Texts Analysis, in: Reliability and Statistics in Transportation and Communication, Lecture Notes in Networks and Systems. Springer International Publishing, Cham, pp. 75–88.
  • Zervina, O., 2022. A Methodology of Automated Identification of Values in the Air Transportation Domain on the Base of E-Texts (PhD Thesis). Transport and Telecommunication Institute, Riga, Latvia.

contact us