ExBigBang: A Dynamic Approach for Explainable Persona Classification through Contextualized Hybrid Transformer Analysis

2025-08-21

AI Summary

Existing user profiling classification methods struggle to effectively integrate heterogeneous contextual information—such as textual descriptions and tabular metadata—while suffering from limited model interpretability, hindering their trustworthy deployment in real-world design scenarios. To address these limitations, we propose a Transformer-based multimodal hybrid architecture that introduces, for the first time, a dynamic recurrent modeling mechanism for user profiling classification. Our approach jointly encodes unstructured text and structured metadata, synergistically fusing domain knowledge with behavioral features to enable fine-grained, context-aware, and temporally adaptive classification. Furthermore, we integrate explainable AI techniques—including attention visualization and feature attribution—to explicitly expose decision rationales. Experiments on benchmark datasets demonstrate that text-table joint modeling yields a +4.2% F1-score improvement over baselines; ablation studies validate the contribution of each component; and interpretability analysis confirms the model’s capacity to identify salient contextual cues.

Technology Category

• Machine Learning: Multimodal Learning
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Bridging structured and unstructured data

Abstract

In user-centric design, persona development plays a vital role in understanding user behaviour, capturing needs, segmenting audiences, and guiding design decisions. However, the growing complexity of user interactions calls for a more contextualized approach to ensure designs align with real user needs. While earlier studies have advanced persona classification by modelling user behaviour, capturing contextual information, especially by integrating textual and tabular data, remains a key challenge. These models also often lack explainability, leaving their predictions difficult to interpret or justify. To address these limitations, we present ExBigBang (Explainable BigBang), a hybrid text-tabular approach that uses transformer-based architectures to model rich contextual features for persona classification. ExBigBang incorporates metadata, domain knowledge, and user profiling to embed deeper context into predictions. Through a cyclical process of user profiling and classification, our approach dynamically updates to reflect evolving user behaviours. Experiments on a benchmark persona classification dataset demonstrate the robustness of our model. An ablation study confirms the benefits of combining text and tabular data, while Explainable AI techniques shed light on the rationale behind the model's predictions.

Problem

• Classifying personas with contextual hybrid data integration
• Addressing explainability gaps in persona prediction models
• Dynamically updating user profiles for evolving behaviors

Innovation

• Hybrid text-tabular transformer for contextual classification
• Dynamic cyclical updating of user behavior profiles
• Explainable AI techniques for prediction rationale interpretation