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

TL;DR

ExBigBang introduces a hybrid transformer-based model that dynamically classifies user personas by integrating textual, tabular, and contextual data, enhancing explainability and adaptability to evolving user behaviors.

Contribution

The paper presents a novel hybrid text-tabular transformer model that improves persona classification with explainability and dynamic updating capabilities.

Findings

Model achieves robust classification performance on benchmark datasets.

Ablation study shows combining text and tabular data improves accuracy.

Explainability techniques clarify the model's decision-making process.

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.