Log in to star items.
- Convenor:
-
Aliya Sarsekeyeva
(Kazakhstan Sociology Lab, Corporate Fund Fund El Umiti)
Send message to Convenor
- Chair:
-
Darkhan Medeuov
- Discussant:
-
Dmitrii Serebrennikov
(Kazakhstan Sociology Lab, El Umiti Foundation)
- Format:
- Panel
- Theme:
- Sociology & Social Issues
Abstract
This panel discussion aims to explore the opportunities and limitations of applying computational methods to research on Central Asia. It will bring together researchers working at the intersection of the social and computational sciences to share experiences, present new empirical studies, and discuss the prospects for the development of this field in a regional context.
One of the most rapidly evolving fields in contemporary social research is the application of computational social science (CSS) methods. This approach focuses on the use of computational methods and algorithms to analyze complex social processes by working with large datasets. Within the framework of CSS, methods such as machine learning, natural language processing (NLP), social network analysis (SNA), agent-based modeling, and experimental methods are actively employed. These tools enable researchers to identify hidden patterns in social interactions, analyze the dynamics of public opinion, study the spread of information, and model the behavior of social groups.
Research in computational social science lies at the intersection of the social sciences, humanities, and computing disciplines. It brings together scholars from fields such as sociology, economics, political science, psychology, cognitive science, management, and communication studies, as well as experts from the natural sciences. This interdisciplinary nature of CSS allows for the integration of theoretical approaches from the social sciences with high-tech analytical tools, creating new opportunities for studying complex social processes.
The development of computational social sciences is particularly relevant for research on Central Asian countries. In recent years, the region has been undergoing an active digital transformation, during which the volume of digital traces created by users in the online space has increased. This data opens up new opportunities for studying social, economic, and political dynamics in the region. Particular attention will be paid to the prospects for applying computational social science methods in the fields of education and medicine, as well as to the broader significance of these methods for sociology as a whole.
Accepted papers
Abstract
Following Lazer et al.'s (2009) article, computational social science is often described as an interdisciplinary field merging social and computational sciences. However, the actual disciplinary status of this field remains unclear. This article examines whether computational social science has emerged as a fully fledged interdisciplinary discipline or whether it functions rather as a multidisciplinary research project. The theoretical framework draws on the distinction between interdisciplinary and multidisciplinary research projects previously applied in studies of the development of cognitive science. While interdisciplinary fields involve the formation of a new disciplinary identity and institutional infrastructure, multidisciplinary projects represent collaborations between existing disciplines without the emergence of an independent scientific field.
The empirical part of the study is based on an analysis of educational programs in computational social science collected from the community-curated repository Awesome Computational Social Science, initiated by the GESIS Institute and maintained by the research community. For each program, data were collected on the year of establishment, program level (BA, MA, PhD), as well as country and region, and a curriculum analysis was conducted. Course titles were coded according to SCOPUS disciplinary categories: each course was assigned up to three disciplinary tags, which were then aggregated into broader categories (STEM, Social Sciences and Humanities (SSH), CSS, and Other). Courses were further classified by type (core/elective) and content (field/method).
These results allow us to assess the disciplinary structure of CSS educational programs and its evolution over time, as well as to answer the question of whether computational social science is emerging as an integrated interdisciplinary field or remains a multidisciplinary configuration dominated by computational and methodological approaches. They also allow us to assess the extent to which CSS is being formed as an independent discipline, whether the expansion of educational programs in this area is justified, and which regional models of their development (USA, Europe, Asia) can serve as a guide for the further institutional development of this field.
Abstract
This study examines the factors that explain differences in academic performance among students with similar cognitive abilities in rural schools in Kazakhstan, using one region as a case study. The theoretical foundation of the study is the value-added concept, according to which students’ educational outcomes are determined not only by their individual characteristics but also by external factors, such as the school’s contribution or the family’s socioeconomic status.
The empirical basis consists of data from the “Myn Bala” National Olympiad, information about students’ grades and families, and school characteristics from the National Education Database. The analysis utilized regression models and a comparison of school grades with Olympiad results as an external indicator of cognitive abilities and academic potential. Methodologically, this work aligns with quantitative sociology and computational social science, combining computational approaches and the analysis of multilevel data to study the factors of educational inequality.
The results showed that students’ individual characteristics influence educational outcomes more strongly than school parameters, although certain features of the school context also prove to be significant. A comparison of school grades and Olympiad results revealed differences that may indicate the subjectivity of internal assessment and an uneven distribution of the school’s “value-added effect” among different social groups of students. Thus, the study demonstrates that the value-added theory is useful for analyzing educational inequality in rural schools in Kazakhstan, as it allows for the consideration of academic performance as the result of the interaction between a student’s individual resources, family capital, and the school’s institutional contribution.
Abstract
In the context of healthcare digitalisation in Central Eurasia, pre hospital Patient Decision Support Systems (PDSS) are gaining importance as tools for guiding patients before they seek in person care. Existing triage protocols (e.g., NHS Pathways or Schmitt–Thompson algorithms) are designed for interactive settings that rely on sequential clarification questions. Applying such protocols to static, unstructured layperson narratives presents a methodological challenge. Due to limited clinical context, both human annotators and artificial intelligence (AI) systems tend to overestimate risk (up triage) following a “safety first” heuristic, which may lead to biased interpretations and reduced practical usefulness.
This study addresses the first stage of developing a system of Medical Action Recommendation from Layperson Narratives (MARLaN) by focusing on dataset construction and annotation design. We propose a four level classification framework for pre triage of layperson texts that integrates international approaches to legitimising “self care” outcomes with national medical triage standards of the Republic of Kazakhstan (Ministry of Healthcare Orders No. 27 and No. 225/2020). A key feature of the scheme is the inclusion of an “Insufficient Data” category (Grey Zone), which captures cases where available information is inadequate for safe decision-making and reduces forced or speculative judgments.
The dataset is developed in collaboration with medical professionals, who annotate layperson-style health queries according to a structured codebook. This resource enables analysis of how individuals without medical training describe symptoms and how such narratives can be systematically interpreted within a local healthcare context. When fully implemented, the proposed approach (MARLaN) may contribute to safer patient routing by reducing the risk of missing cases requiring immediate medical attention, while also helping to alleviate unnecessary healthcare visits through appropriate use of self-care recommendations, thereby allowing healthcare systems to focus resources on patients with genuine need.
From a regional perspective, the study contributes to ongoing discussions on healthcare accessibility, digital mediation, and patient behavior in Central Eurasia, and provides a practical foundation for future development of AI-assisted patient routing tools adapted to local institutional frameworks.
Abstract
A growing body of research suggests that students’ academic outcomes are shaped not only by individual and family characteristics but also by the environments in which they learn. However, the role of everyday physical surroundings remains insufficiently measured and understood. This study aims to identify the relationship between the physical characteristics of school environments and student academic performance, using general education schools in Astana as a case study. We propose a methodology that integrates the analysis of Google Street View (GSV) panoramic images with modern vision-language models (VLM). We extract a comprehensive set of interpretable urban environment features—including perceived safety, landscaping, and socio-economic markers—to integrate them with the results of the Unified National Testing (UNT). The methodological novelty of this research lies in the creation of a unified analytical pipeline that integrates computer vision techniques (Qwen3-VL-8B, StreetLens), the extraction of self-supervised embeddings (DINOv2 ViT-L), and quantitative sociological analysis. Unlike traditional studies that rely on aggregated statistics, our approach utilizes high-resolution spatial data to capture the micro-context of the school environment.