Sequential Tag Recommendation

TL;DR

This paper introduces a tag recommendation algorithm that models user behavior sequences to capture dynamic interests, improving tag suggestions by considering user preferences alongside post content.

Contribution

It proposes a novel MLP-based method that incorporates user historical posting and tagging data to enhance tag recommendation accuracy.

Findings

Effective modeling of user interest dynamics.

Improved tag recommendation performance.

Utilizes sequence modeling with MLP for interest extraction.

Abstract

With the development of Internet technology and the expansion of social networks, online platforms have become an important way for people to obtain information. The introduction of tags facilitates information categorization and retrieval. Meanwhile, the development of tag recommendation systems not only enables users to input tags more efficiently, but also improves the quality of tags. However, current tag recommendation methods only consider the content of the current post and do not take into account the influence of user preferences. Since the main body of tag recommendation is the user, it is very necessary to obtain the user's tagging habits. Therefore, this paper proposes a tag recommendation algorithm (MLP4STR) based on the dynamic preference of user's behavioral sequence, which models the user's historical post information and historical tag information to obtain the user's dynamic interest changes. A pure MLP structure across feature dimensions is used in sequence modeling to model the interaction between tag content and post content to fully extract the user's interests. Finally tag recommendation is performed.