Modeling User Behavior from Adaptive Surveys with Supplemental Context
This work addresses the challenge of enhancing behavior modeling for industries relying on surveys, offering a practical and extensible solution, though it appears incremental as it builds on existing methods by integrating supplemental data.
The paper tackled the problem of modeling user behavior from surveys, which are limited by fatigue and incomplete responses, by proposing LANTERN, a modular architecture that fuses adaptive survey responses with supplemental contextual signals, achieving improved multi-label prediction of survey responses compared to survey-only baselines.
Modeling user behavior is critical across many industries where understanding preferences, intent, or decisions informs personalization, targeting, and strategic outcomes. Surveys have long served as a classical mechanism for collecting such behavioral data due to their interpretability, structure, and ease of deployment. However, surveys alone are inherently limited by user fatigue, incomplete responses, and practical constraints on their length making them insufficient for capturing user behavior. In this work, we present LANTERN (Late-Attentive Network for Enriched Response Modeling), a modular architecture for modeling user behavior by fusing adaptive survey responses with supplemental contextual signals. We demonstrate the architectural value of maintaining survey primacy through selective gating, residual connections and late fusion via cross-attention, treating survey data as the primary signal while incorporating external modalities only when relevant. LANTERN outperforms strong survey-only baselines in multi-label prediction of survey responses. We further investigate threshold sensitivity and the benefits of selective modality reliance through ablation and rare/frequent attribute analysis. LANTERN's modularity supports scalable integration of new encoders and evolving datasets. This work provides a practical and extensible blueprint for behavior modeling in survey-centric applications.