General-Purpose User Modeling with Behavioral Logs: A Snapchat Case Study
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910540586024960 |
|---|---|
| author | Fang, Qixiang Zhou, Zhihan Barbieri, Francesco Liu, Yozen Neves, Leonardo Nguyen, Dong Oberski, Daniel L. Bos, Maarten W. Dotsch, Ron |
| author_facet | Fang, Qixiang Zhou, Zhihan Barbieri, Francesco Liu, Yozen Neves, Leonardo Nguyen, Dong Oberski, Daniel L. Bos, Maarten W. Dotsch, Ron |
| contents | Learning general-purpose user representations based on user behavioral logs is an increasingly popular user modeling approach. It benefits from easily available, privacy-friendly yet expressive data, and does not require extensive re-tuning of the upstream user model for different downstream tasks. While this approach has shown promise in search engines and e-commerce applications, its fit for instant messaging platforms, a cornerstone of modern digital communication, remains largely uncharted. We explore this research gap using Snapchat data as a case study. Specifically, we implement a Transformer-based user model with customized training objectives and show that the model can produce high-quality user representations across a broad range of evaluation tasks, among which we introduce three new downstream tasks that concern pivotal topics in user research: user safety, engagement and churn. We also tackle the challenge of efficient extrapolation of long sequences at inference time, by applying a novel positional encoding method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_12111 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | General-Purpose User Modeling with Behavioral Logs: A Snapchat Case Study Fang, Qixiang Zhou, Zhihan Barbieri, Francesco Liu, Yozen Neves, Leonardo Nguyen, Dong Oberski, Daniel L. Bos, Maarten W. Dotsch, Ron Human-Computer Interaction Information Retrieval Learning general-purpose user representations based on user behavioral logs is an increasingly popular user modeling approach. It benefits from easily available, privacy-friendly yet expressive data, and does not require extensive re-tuning of the upstream user model for different downstream tasks. While this approach has shown promise in search engines and e-commerce applications, its fit for instant messaging platforms, a cornerstone of modern digital communication, remains largely uncharted. We explore this research gap using Snapchat data as a case study. Specifically, we implement a Transformer-based user model with customized training objectives and show that the model can produce high-quality user representations across a broad range of evaluation tasks, among which we introduce three new downstream tasks that concern pivotal topics in user research: user safety, engagement and churn. We also tackle the challenge of efficient extrapolation of long sequences at inference time, by applying a novel positional encoding method. |
| title | General-Purpose User Modeling with Behavioral Logs: A Snapchat Case Study |
| topic | Human-Computer Interaction Information Retrieval |
| url | https://arxiv.org/abs/2312.12111 |