Graph-Based Discovery of Mathematical Software Communities and Publication-to-Community Prediction
2026-08-17 • Information Retrieval
Information Retrieval
AI summaryⓘ
The authors studied how different math software tools are used together in research, forming communities that cross usual subject boundaries. They created a network based on which software appears in research papers and used it to find groups of related software. Then, they tried to predict which software community a paper belongs to by looking at the paper's metadata, comparing detailed subject classifications to just the paper titles. Their results showed that using structured subject codes works better to identify software communities in research than using titles alone. This suggests that organized metadata is useful for discovering and recommending research software.
software co-usage networkcommunity detectionmulti-label classificationMathematics Subject Classification (MSC)title embeddingsresearch softwarepublication metadatamachine learningswMATH dataset
Authors
Maxence Azzouz-Thuderoz, Yuni Susanti, Moritz Schubotz
Abstract
Research software forms distinct co-usage communities that span traditional disciplinary boundaries, yet the structure of these communities remains largely unexplored. We present a graph-based framework for discovering mathematical software communities and predicting their association with research publications. We construct a software co-usage network from publication-software relationships using a curated swMATH dataset and subsequently apply community detection method, revealing a heterogeneous landscape of mathematical software communities. We formulate publication-to-community mapping as a multi-label classification task and further investigate whether community membership can be predicted from lightweight scholarly metadata. Specifically, we compare two feature representations of scientific publications: Mathematics Subject Classification (MSC) and title-based embeddings. Across a range of models, structured MSC representation consistently provides a stronger precision-recall trade-off, demonstrating that structured domain metadata captures software-community structure more effectively than compressed title-only semantics in this setting. This work highlights the continuing value of structured scholarly metadata for large-scale research software discovery, classification and recommendation.