Experience in applying large language models to analyse sociological data obtained as a result of interviews on students’ perception of entrepreneurial activity
Modern society is experiencing a digital transformation of various spheres associated with the development of artificial intelligence and big data. The introduction of large language models (hereinafter referred to as LLM) into scientific research opens new opportunities, but also raises a number of...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
State University of Management
2024-10-01
|
| Series: | Цифровая социология |
| Subjects: | |
| Online Access: | https://digitalsociology.guu.ru/jour/article/view/323 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832540679421558784 |
|---|---|
| author | E. G. Ashikhmin V. V. Levchenko G. I. Seletkova |
| author_facet | E. G. Ashikhmin V. V. Levchenko G. I. Seletkova |
| author_sort | E. G. Ashikhmin |
| collection | DOAJ |
| description | Modern society is experiencing a digital transformation of various spheres associated with the development of artificial intelligence and big data. The introduction of large language models (hereinafter referred to as LLM) into scientific research opens new opportunities, but also raises a number of questions, which makes it relevant to study the peculiarities of their application for qualitative data analysis in sociology. The purpose of this article is to explore how LLM can influence the methodology and practice of sociological research, and to identify the advantages and disadvantages of their application. The authors rely on the use of the Calude-3 LLM to qualitatively analyse empirical data from a sociological study of students’ perception of entrepreneurship. The possibilities of LLM in the analysis of qualitative data are revealed: analysis of sentiment, construction of logical conclusions, classification, clustering, and formation of typologies. The advantages of using LLM are shown: increased data processing speed, saving time and resources. The application of LLM becomes a tool to optimise the research process in sociology, allowing to deepen the analysis of qualitative data, but it also has a number of limitations: social and political bias, difficulties with hallucinations. It is necessary to increase the transparency of models, improve their interpretability and explainability and reduce their social and political bias as well as ethical and legal regulation of the use of LLM models. |
| format | Article |
| id | doaj-art-82d93e04031e47e8b3188ffe426f3d11 |
| institution | Kabale University |
| issn | 2658-347X 2713-1653 |
| language | Russian |
| publishDate | 2024-10-01 |
| publisher | State University of Management |
| record_format | Article |
| series | Цифровая социология |
| spelling | doaj-art-82d93e04031e47e8b3188ffe426f3d112025-02-04T16:32:35ZrusState University of ManagementЦифровая социология2658-347X2713-16532024-10-017341410.26425/2658-347X-2024-7-3-4-14202Experience in applying large language models to analyse sociological data obtained as a result of interviews on students’ perception of entrepreneurial activityE. G. Ashikhmin0V. V. Levchenko1G. I. Seletkova2Perm National Research Polytechnic UniversityPerm National Research Polytechnic UniversityPerm National Research Polytechnic UniversityModern society is experiencing a digital transformation of various spheres associated with the development of artificial intelligence and big data. The introduction of large language models (hereinafter referred to as LLM) into scientific research opens new opportunities, but also raises a number of questions, which makes it relevant to study the peculiarities of their application for qualitative data analysis in sociology. The purpose of this article is to explore how LLM can influence the methodology and practice of sociological research, and to identify the advantages and disadvantages of their application. The authors rely on the use of the Calude-3 LLM to qualitatively analyse empirical data from a sociological study of students’ perception of entrepreneurship. The possibilities of LLM in the analysis of qualitative data are revealed: analysis of sentiment, construction of logical conclusions, classification, clustering, and formation of typologies. The advantages of using LLM are shown: increased data processing speed, saving time and resources. The application of LLM becomes a tool to optimise the research process in sociology, allowing to deepen the analysis of qualitative data, but it also has a number of limitations: social and political bias, difficulties with hallucinations. It is necessary to increase the transparency of models, improve their interpretability and explainability and reduce their social and political bias as well as ethical and legal regulation of the use of LLM models.https://digitalsociology.guu.ru/jour/article/view/323large language modelsllmdigital toolsqualitative data analysisinterview analysissociological research methodsdigital transformationsentiment analysisdata preprocessing algorithmclustering |
| spellingShingle | E. G. Ashikhmin V. V. Levchenko G. I. Seletkova Experience in applying large language models to analyse sociological data obtained as a result of interviews on students’ perception of entrepreneurial activity Цифровая социология large language models llm digital tools qualitative data analysis interview analysis sociological research methods digital transformation sentiment analysis data preprocessing algorithm clustering |
| title | Experience in applying large language models to analyse sociological data obtained as a result of interviews on students’ perception of entrepreneurial activity |
| title_full | Experience in applying large language models to analyse sociological data obtained as a result of interviews on students’ perception of entrepreneurial activity |
| title_fullStr | Experience in applying large language models to analyse sociological data obtained as a result of interviews on students’ perception of entrepreneurial activity |
| title_full_unstemmed | Experience in applying large language models to analyse sociological data obtained as a result of interviews on students’ perception of entrepreneurial activity |
| title_short | Experience in applying large language models to analyse sociological data obtained as a result of interviews on students’ perception of entrepreneurial activity |
| title_sort | experience in applying large language models to analyse sociological data obtained as a result of interviews on students perception of entrepreneurial activity |
| topic | large language models llm digital tools qualitative data analysis interview analysis sociological research methods digital transformation sentiment analysis data preprocessing algorithm clustering |
| url | https://digitalsociology.guu.ru/jour/article/view/323 |
| work_keys_str_mv | AT egashikhmin experienceinapplyinglargelanguagemodelstoanalysesociologicaldataobtainedasaresultofinterviewsonstudentsperceptionofentrepreneurialactivity AT vvlevchenko experienceinapplyinglargelanguagemodelstoanalysesociologicaldataobtainedasaresultofinterviewsonstudentsperceptionofentrepreneurialactivity AT giseletkova experienceinapplyinglargelanguagemodelstoanalysesociologicaldataobtainedasaresultofinterviewsonstudentsperceptionofentrepreneurialactivity |