Addressing Cold Start For next-article Recommendation

TL;DR

This study adapts the ALMM model for news recommendation to improve cold-start performance by using sequential click behavior and content features like BERT and TF-IDF, showing improved accuracy over baselines.

Contribution

The paper introduces a modified ALMM model tailored for news recommendation, incorporating sequential behavior and content features to enhance cold-start recommendations.

Findings

ALMM with TF-IDF improves recommendation accuracy in cold-start scenarios.

Sequential modeling of news clicks enhances robustness over baseline models.

Minimal modifications to ALMM are insufficient for effective news recommendation.

Abstract

This replication study modifies ALMM, the Adaptive Linear Mapping Model constructed for the next song recommendation, to the news recommendation problem on the MIND dataset. The original version of ALMM computes latent representations for users, last-time items, and current items in a tensor factorization structure and learns a linear mapping from content features to latent item vectors. Our replication aims to improve recommendation performance in cold-start scenarios by restructuring this model to sequential news click behavior, viewing consecutively read articles as (last news, next news) tuples. Instead of the original audio features, we apply BERT and a TF-IDF (Term Frequency-Inverse Document Frequency) to news titles and abstracts to extract token contextualized representations and align them with triplet-based user reading patterns. We also propose a reproducibly thorough pre-processing pipeline combining news filtering and feature integrity validation. Our implementation of ALMM with TF-IDF shows relatively improved recommendation accuracy and robustness over Forbes and Oord baseline models in the cold-start scenario. We demonstrate that ALMM in a minimally modified state is not suitable for next news recommendation.