Toward a Robust Diversity-Based Model to Detect Changes of Context

TL;DR

This paper introduces a real-time, diversity-based model for detecting user context changes in recommender systems, demonstrating robustness across various data conditions and item types.

Contribution

It proposes a generic, constant-time model for detecting context changes based on diversity, applicable across domains and item types, with validation on a large music dataset.

Findings

Model is robust to data sparsity and item diversity.

Effective in detecting session ends and context shifts.

Applicable across different online service domains.

Abstract

Being able to automatically and quickly understand the user context during a session is a main issue for recommender systems. As a first step toward achieving that goal, we propose a model that observes in real time the diversity brought by each item relatively to a short sequence of consultations, corresponding to the recent user history. Our model has a complexity in constant time, and is generic since it can apply to any type of items within an online service (e.g. profiles, products, music tracks) and any application domain (e-commerce, social network, music streaming), as long as we have partial item descriptions. The observation of the diversity level over time allows us to detect implicit changes. In the long term, we plan to characterize the context, i.e. to find common features among a contiguous sub-sequence of items between two changes of context determined by our model. This will allow us to make context-aware and privacy-preserving recommendations, to explain them to users. As this is an ongoing research, the first step consists here in studying the robustness of our model while detecting changes of context. In order to do so, we use a music corpus of 100 users and more than 210,000 consultations (number of songs played in the global history). We validate the relevancy of our detections by finding connections between changes of context and events, such as ends of session. Of course, these events are a subset of the possible changes of context, since there might be several contexts within a session. We altered the quality of our corpus in several manners, so as to test the performances of our model when confronted with sparsity and different types of items. The results show that our model is robust and constitutes a promising approach.