Multi-Scenario User Profile Construction via Recommendation Lists

TL;DR

This paper introduces RAPI, a framework that constructs user profiles across multiple scenarios by analyzing recommendation lists using content embeddings and adaptive weighting, improving inference accuracy.

Contribution

The paper presents a novel, scenario-agnostic user profiling framework leveraging recommendation lists, BERT embeddings, and adaptive weighting for improved accuracy.

Findings

Achieves inference accuracy of 0.764 and 0.6477 on two datasets.

Effectively infers user characteristics across four analytical scenarios.

Utilizes content embeddings and adaptive weights for robust user profiling.

Abstract

Recommender systems (RS) play a core role in various domains, including business analytics, helping users and companies make appropriate decisions. To optimize service quality, related technologies focus on constructing user profiles by analyzing users' historical behavior information. This paper considers four analytical scenarios to evaluate user profiling capabilities under different information conditions. A generic user attribute analysis framework named RAPI is proposed, which infers users' personal characteristics by exploiting easily accessible recommendation lists. Specifically, a surrogate recommendation model is established to simulate the original model, leveraging content embedding from a pre-trained BERT model to obtain item embeddings. A sample augmentation module generates extended recommendation lists by considering similarity between model outputs and item embeddings. Finally, an adaptive weight classification model assigns dynamic weights to facilitate user characteristic inference. Experiments on four collections show that RAPI achieves inference accuracy of 0.764 and 0.6477, respectively.