Catalog-style synopsis of a conference entry: Forensic footprints in digital love. Unveiling romance scams with Maltego and machine learning. AIP conference proceedings. The entry surveys how romance scams manifest in online interactions and how digital-forensics methods can map and interpret these activities. Central to the discussion is the integration of Maltego, a graph-based data-mining and link-analysis platform, with machine-learning approaches to detect patterns associated with fraudulent outreach. The data landscape is described in general terms as comprising online profiles, messaging interactions, and network connections, with attention to data fusion and entity-resolution that produce a coherent representation of actors and events. Graph-analytic techniques are highlighted as a means to illuminate relationships among victims, scammers, and auxiliary entities, supporting the reconstruction of scam workflows and the typical stages of operation, from initial outreach to exploitation. The synopsis outlines a methodological framework aimed at detection, investigation, and evidence interpretation, emphasizing repeatable workflows and model-interpretability. It positions Maltego as a connective layer that links forensic data with machine-learning signals, enabling investigators to explore complex datasets through visual graphs and accompanying analytical features. Key elements include preprocessing steps, feature extraction from textual content and metadata, and model-selection choices for anomaly detection or classification tasks. The entry also discusses limitations related to data quality, platform variability, and ethical considerations surrounding sensitive information and privacy. Potential applications mentioned include early warning and case triage, as well as support for evidentiary disclosure in proceedings. Overall, the work situates the approach within larger efforts to combine perceptual tools and computational methods for analyzing digital fraud in intimate-context settings.