Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.13667 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909115050098688 |
|---|---|
| author | Zhou, Jianghui Gao, Ya Liu, Jie Zhao, Xuemin Yang, Zhaohua Wu, Yue Shi, Lirong |
| author_facet | Zhou, Jianghui Gao, Ya Liu, Jie Zhao, Xuemin Yang, Zhaohua Wu, Yue Shi, Lirong |
| contents | Large language models(LLM) such as ChatGPT have substantially simplified the generation of marketing copy, yet producing content satisfying domain specific requirements, such as effectively engaging customers, remains a significant challenge. In this work, we introduce the Genetic Copy Optimization Framework (GCOF) designed to enhance both efficiency and engagememnt of marketing copy creation. We conduct explicit feature engineering within the prompts of LLM. Additionally, we modify the crossover operator in Genetic Algorithm (GA), integrating it into the GCOF to enable automatic feature engineering. This integration facilitates a self-iterative refinement of the marketing copy. Compared to human curated copy, Online results indicate that copy produced by our framework achieves an average increase in click-through rate (CTR) of over $50\%$. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_13667 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GCOF: Self-iterative Text Generation for Copywriting Using Large Language Model Zhou, Jianghui Gao, Ya Liu, Jie Zhao, Xuemin Yang, Zhaohua Wu, Yue Shi, Lirong Computation and Language Large language models(LLM) such as ChatGPT have substantially simplified the generation of marketing copy, yet producing content satisfying domain specific requirements, such as effectively engaging customers, remains a significant challenge. In this work, we introduce the Genetic Copy Optimization Framework (GCOF) designed to enhance both efficiency and engagememnt of marketing copy creation. We conduct explicit feature engineering within the prompts of LLM. Additionally, we modify the crossover operator in Genetic Algorithm (GA), integrating it into the GCOF to enable automatic feature engineering. This integration facilitates a self-iterative refinement of the marketing copy. Compared to human curated copy, Online results indicate that copy produced by our framework achieves an average increase in click-through rate (CTR) of over $50\%$. |
| title | GCOF: Self-iterative Text Generation for Copywriting Using Large Language Model |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2402.13667 |