Rethinking Thematic Evolution in Science Mapping: An Integrated Framework for Longitudinal Analysis

Strategic diagrams and co-word analysis are widely employed to examine the conceptual structure of scientific domains and their development over time. Yet a structural inconsistency characterises dominant longitudinal implementations: themes are detected through relational clustering in weighted networks, whereas their inter-temporal connections are commonly inferred from set-theoretic overlap among keywords or core documents. This study introduces a structurally integrated framework in which lineage reconstruction is embedded within the same weighted relational architecture that underpins cross-sectional detection. The approach models thematic continuity through graded document affiliation and a lineage-strength measure integrating directional thematic coverage and centrality-weighted structural coherence, thereby reconceptualising evolution as the reconfiguration of relational structures rather than the persistence of surface vocabulary. An empirical application to the complete publication record of the Journal of Informetrics (2007--2025), together with a comparative assessment against standard thematic analysis, shows that this specification captures differentiated split-and-merge dynamics that inclusion-based methods tend to obscure. It also reduces hub-centred artefacts arising from purely lexical lineage reconstruction. By aligning thematic detection and temporal modelling within a unified relational paradigm, the framework enhances the methodological coherence and interpretive robustness of longitudinal science mapping.