Abstract
Automatic monitoring systems for inappropriate user-generated messages have been found to be effective in reducing human operation costs in Consumer to Consumer (C2C) marketplace services, in which customers send messages directly to other customers.We propose a lightweight neural network that takes a conversation as input, which we deployed to a production service.Our results show that the system reduced the human operation costs to less than one-sixth compared to the conventional rule-based monitoring at Mercari.- Anthology ID:
- 2022.ecnlp-1.8
- Volume:
- Proceedings of the Fifth Workshop on e-Commerce and NLP (ECNLP 5)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Venue:
- ECNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 58–62
- Language:
- URL:
- https://aclanthology.org/2022.ecnlp-1.8
- DOI:
- 10.18653/v1/2022.ecnlp-1.8
- Cite (ACL):
- Yusuke Shido, Hsien-Chi Liu, and Keisuke Umezawa. 2022. Textual Content Moderation in C2C Marketplace. In Proceedings of the Fifth Workshop on e-Commerce and NLP (ECNLP 5), pages 58–62, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Textual Content Moderation in C2C Marketplace (Shido et al., ECNLP 2022)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2022.ecnlp-1.8.pdf