The integration of artificial intelligence in library services has the potential to revolutionize how information is accessed, managed, and interpreted. For social sciences, AI offers unique opportunities to enhance data-driven research, streamline resource management, and provide new insights for diverse social phenomena. In this webinar we will address key issues, innovative practices, and ethical considerations for librarians in the social sciences field who aim to leverage AI to meet evolving librarian and user needs.

Presentations

AI Tools for Systematic Review: Opportunities and Challenges

by Muhammad Yousuf Ali (Karachi, Pakistan)

Abstract: AI tools have significantly impacted academia and research, providing valuable support for various research activities. In recent years, a variety of AI-based tools have emerged to assist scholars and researchers, making their research processes more efficient. One important technique in research is the systematic review, which is commonly used in both the health sciences and social sciences.

Libraries play a crucial role in supporting different types of literature reviews, including narrative reviews, scoping reviews, systematic reviews, and meta-analyses. This presentation aims to highlight AI tools used in systematic reviews and how librarians teach these tools to help library users conduct effective systematic reviews by integrating AI technology. Topics covered in this presentation include literature review summary tools such as Semantic Scholar, Elicit, and Research Rabbit, along with screening tools like ASReview, Rayyan, and Covidance for data management. We will also discuss reference and citation management tools like Samwell AI, myBib, and EasyBib.

 

Enhancing Social Science Research in Library Discovery: The Application of Generative AI for Contextual and Exploratory Search

by Mr. Luis Ezra D. Cruz (Manila, Philippines)

Abstract: Emerging models of information retrieval are reshaping how researchers in the social sciences navigate complex and interdisciplinary literature. As scholarly output grows in volume and complexity, traditional keyword-based search methods often fall short in meeting the needs of exploratory and context-driven inquiry. This prompts libraries to adopt AI-enhanced discovery tools that support more intuitive research workflows.

This paper examines the Primo Research Assistant, a generative AI-supported tool integrated into the Primo-based discovery platform of an academic library in Southeast Asia. The tool is designed to facilitate exploratory search through natural language querying and contextualized content delivery. Operating within the Primo VE discovery layer, it enables users to pose research questions in natural language. Using a Retrieval-Augmented Generation (RAG) framework, it identifies and synthesizes content drawn from indexed academic sources in the Central Discovery Index (CDI). The resulting output presents a concise, structured overview derived from article abstracts, accompanied by inline citations and links to the full records, allowing users to verify and further explore the presented content.

The paper focuses on the tool’s application in research contexts, particularly its role in supporting preliminary literature scanning, clarifying unfamiliar topics, and enabling associative discovery, an information behavior commonly observed in social sciences scholarship. Use cases include users refining research questions, identifying entry points into emerging subject areas, and surfacing relevant materials when initial keyword strategies yield limited results. The tool also proves helpful in guiding users toward adjacent topics and concepts that may not have been part of their original query formulation.

Preliminary observations indicate that the tool is valued for its ability to summarize dispersed content, reduce time spent navigating search results, and provide starting points for deeper inquiry. Users describe it as particularly useful in situations involving topic selection, scoping reviews, and initial background research.

 

Bibliographic Activity in Social Sciences in the Era of Neural Networks and API Interfaces

by Vadim K. Stepanov (Moscow, Russia)

Abstract: The total digitalization of information transfer processes and the parallel development of several standards and technologies at once have formed a new paradigm of bibliographic and, in general, information services for the scientific sphere. The foundation of the transformation was the adoption of international standards DOI and ORCID. The method of providing scientific papers has also been unified: in most global scientific journals, when the author uploads a manuscript, along with the full text, all accompanying metadata are entered, launching the entire further cycle of bibliographic information.

When a scientific paper is published, information about it is automatically transferred to Crossref (the global DOI registration agency), which has become a giant global repository of bibliographic information continuously received from publishers. Crossref is an open resource, information from which can be obtained by anyone without restrictions. API technology is used to borrow data from the Internet, which has become the basis for the bibliographic data exchange system: due to API, bibliographic information is continuously transferred from resource to resource in previously unimaginable gigantic volumes in the background without any human intervention.

The opportunities that have opened up have been taken advantage of by companies that can be described as global discovery services or global bibliographic platforms. Their goal is to unite the entire world flow of scientific publications in order to provide a full cycle of information services to any user in strict accordance with their individual information needs. Receiving bibliographic information from many publishers and specialized services, they have already accumulated arrays of hundreds of millions of records. The data is subject to intellectual processing – information obtained from different sources is combined into a single bibliographic record. Based on this array, users are provided with all traditional types of information support for research activities in a fully automated mode. Today, such companies include Semantic Scholar, The Lens, OpenAlex, Scilit, Google Academy, ResearchGate, Scopus, Web of Science. In Russia, the equivalent of such an academic service is Elibrary.

In the future, information support will increasingly shift towards global bibliographic platforms that provide comprehensive data with maximum comfort. Bibliographic services around the world need to take this fact into account and shift the focus to processing printed retrospective data and the flow of serials that are not classified as scientific publications.

 

AI-Assisted Emotional Tagging in Social Sciences Libraries: Enhancing Empathetic Information Access

by Ashutosh Kumar SURAJ (Chandauli, India)

Abstract: In today’s rapidly evolving information landscape, libraries are no longer just repositories of knowledge; they are empathetic spaces that cater to the diverse needs of users. Social Sciences libraries, dealing with sensitive topics such as gender inequality, domestic violence, and mental health, face a challenge in categorizing content in a way that acknowledges its emotional impact on readers. Traditional classification systems focus on academic relevance but overlook the emotional sensitivity required for such topics.

This presentation proposes an innovative solution: the integration of AI-assisted emotional tagging in Social Sciences libraries. By applying AI tools like sentiment analysis and contextual emotion recognition, library content can be tagged with emotional labels such as “empathetic,” “neutral,” or “potentially distressing.” This system will allow users to filter materials based on their emotional comfort, empowering them to engage with sensitive content according to their mental and emotional readiness.

The presentation will explore the methodology behind developing such a system, including dataset curation, AI training, and the incorporation of user profiles for personalized suggestions. Key innovations like AI-generated content warnings and librarian training for emotional intelligence will also be discussed.