Discovering Research Hypotheses in Social Science Using Knowledge Graph Embeddings

Abstract

General rightsCopyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights.• Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal ? Take down policyIf you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.

Relationship Prediction in a Knowledge Graph Embedding Model of the Illicit Antiquities Trade

“…However, it might be that graph embedding models could surface interesting patterns or insights based on patterns in the multidimensional space. In de Haan et alia (2021), the authors create a knowledge graph from an open-access repository of research results (the Cooperation Databank) to generate a graph connecting scientific observations with the published results, and then they use a knowledge graph embedding model (via AmpliGraph) to generate hypotheses about the domain likely to be true. Similar approaches are used in bioinformatics for new drug prediction or disease response (Zhu et al 2022).…”

CS-KG: A Large-Scale Knowledge Graph of Research Entities and Claims in Computer Science

“…CS-KG can support several intelligent services that require a high quality representation of research concepts and currently rely on alternative knowledge bases which cover a smaller number of publications (e.g., AI-KG, ORKG, Nanopublications) or offer a less granular conceptualization of the domain (Seman-ticScholar, OpenAlex, AIDA). These include systems for supporting machinereadable surveys [46,30], tools for generating research hypothesis [20] and detecting contradictory research claims [3], ontology-driven topic models (e.g., CoCoNoW [5]), recommender systems for articles (e.g., SBR [41]) and video lessons [7], visualisation frameworks (e.g., ScholarLensViz [26], ConceptScope [47]), scholarly knowledge graph embeddings (e.g., Trans4E [29]), tools for identifying domain experts (e.g., VeTo [42]), and systems for predicting research impact (e.g., ArtSim [13]).…”

Completing Scientific Facts in Knowledge Graphs of Research Concepts

“…The resulting embedding space is subsequently used to evaluate the likelihood of a candidate triple to be correct or incorrect, since entities that are supposed to be related by means of a certain relation are expected to be closer to each other in the embedding space. They have also been recently used for assessing research hypotheses, yielding promising results [3].…”

“…One of the main challenges in this space is to generate a semantically rich, interlinked, and machine readable description of the research knowledge that could support more sophisticated services for analysing the scientific literature, forecasting research dynamics, generating scientific hypothesis, identifying key insights, informing funding decision, confirming claims in news, automatically running experi-ments, and so on [2,3,4].…”

“…The evaluation shows that SciCheck significantly outperforms nine alternative approaches in terms of precision, which we consider key for reliably extending knowledge graphs of research concepts, while still obtaining good values of recall. All the resources used for evaluation are available online 3 .…”