Session Recommendations with Song Features Based on Transformer

DOI

10.2991/978-94-6463-304-7_9How to use a DOI?

Keywords

conversation recommendation; transformer; long-term and short-term recommendation

Abstract

With the advent of the information age and the explosive growth of data, it is difficult for people to find the content they are interested in, and the recommendation system came into being. In recent years, the session recommendation in the recommendation system has attracted the attention of many people, which is obviously different from the traditional recommendation. The traditional recommendation, such as collaborative filtering, is to find similar users or similar items for recommendation, while the session recommendation is to recommend according to the interaction behavior between users and items, so that dynamic recommendation can be made according to the changes in users' interests. In this article, we first proposed to use the transformer based method to learn the historical behavior of users and the label characteristics of each song, then search the item set that is most similar to the last item in the session through the itemknn method, and mix it proportionally to form the final recommendation list. At last, a large number of experiments are carried out to prove the superiority of our method.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Shuyi Li
PY  - 2023
DA  - 2023/12/04
TI  - Session Recommendations with Song Features Based on Transformer
BT  - Proceedings of the 3rd International Conference on Digital Economy and Computer Application (DECA 2023)
PB  - Atlantis Press
SP  - 73
EP  - 80
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-304-7_9
DO  - 10.2991/978-94-6463-304-7_9
ID  - Li2023
ER  -