Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.07885 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909832583315456 |
|---|---|
| author | Hagiri, Madoka Okamoto, Kazushi Karube, Koki Harada, Kei Shibata, Atsushi |
| author_facet | Hagiri, Madoka Okamoto, Kazushi Karube, Koki Harada, Kei Shibata, Atsushi |
| contents | Complementary recommendations suggest combinations of useful items that play important roles in e-commerce. However, complementary relationships are often subjective and vary among individuals, making them difficult to infer from historical data. Unlike conventional history-based methods that rely on statistical co-occurrence, we focus on the underlying usage context that motivates item combinations. We hypothesized that people select complementary items by imagining specific usage scenarios and identifying the needs in such situations. Based on this idea, we explored the use of large language models (LLMs) to generate item usage scenarios as a starting point for constructing complementary recommendation systems. First, we evaluated the plausibility of LLM-generated scenarios through manual annotation. The results demonstrated that approximately 85% of the generated scenarios were determined to be plausible, suggesting that LLMs can effectively generate realistic item usage scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_07885 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Generation and annotation of item usage scenarios in e-commerce using large language models Hagiri, Madoka Okamoto, Kazushi Karube, Koki Harada, Kei Shibata, Atsushi Information Retrieval Complementary recommendations suggest combinations of useful items that play important roles in e-commerce. However, complementary relationships are often subjective and vary among individuals, making them difficult to infer from historical data. Unlike conventional history-based methods that rely on statistical co-occurrence, we focus on the underlying usage context that motivates item combinations. We hypothesized that people select complementary items by imagining specific usage scenarios and identifying the needs in such situations. Based on this idea, we explored the use of large language models (LLMs) to generate item usage scenarios as a starting point for constructing complementary recommendation systems. First, we evaluated the plausibility of LLM-generated scenarios through manual annotation. The results demonstrated that approximately 85% of the generated scenarios were determined to be plausible, suggesting that LLMs can effectively generate realistic item usage scenarios. |
| title | Generation and annotation of item usage scenarios in e-commerce using large language models |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2510.07885 |