Exploiting Session Information in BERT-based Session-aware Sequential Recommendation

04/22/2022
by   Jinseok Seol, et al.
0

In recommendation systems, utilizing the user interaction history as sequential information has resulted in great performance improvement. However, in many online services, user interactions are commonly grouped by sessions that presumably share preferences, which requires a different approach from ordinary sequence representation techniques. To this end, sequence representation models with a hierarchical structure or various viewpoints have been developed but with a rather complex network structure. In this paper, we propose three methods to improve recommendation performance by exploiting session information while minimizing additional parameters in a BERT-based sequential recommendation model: using session tokens, adding session segment embeddings, and a time-aware self-attention. We demonstrate the feasibility of the proposed methods through experiments on widely used recommendation datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/25/2019

Neighborhood-Enhanced and Time-Aware Model for Session-based Recommendation

Session based recommendation has become one of the research hotpots in t...
research
11/20/2020

Exploring Global Information for Session-based Recommendation

Session-based recommendation (SBR) is a challenging task, which aims at ...
research
06/15/2021

An Automated Quality Evaluation Framework of Psychotherapy Conversations with Local Quality Estimates

Computational approaches for assessing the quality of conversation-based...
research
11/13/2017

Neural Attentive Session-based Recommendation

Given e-commerce scenarios that user profiles are invisible, session-bas...
research
09/30/2022

A Sequence-Aware Recommendation Method Based on Complex Networks

Online stores and service providers rely heavily on recommendation softw...
research
10/07/2022

KAST: Knowledge Aware Adaptive Session Multi-Topic Network for Click-Through Rate Prediction

Capturing the evolving trends of user interest is important for both rec...
research
09/30/2021

USER: A Unified Information Search and Recommendation Model based on Integrated Behavior Sequence

Search and recommendation are the two most common approaches used by peo...

Please sign up or login with your details

Forgot password? Click here to reset