PopALM: Popularity-Aligned Language Models for Social Media Trendy Response Prediction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910348366315520 |
|---|---|
| author | Yu, Erxin Li, Jing Xu, Chunpu |
| author_facet | Yu, Erxin Li, Jing Xu, Chunpu |
| contents | Social media platforms are daily exhibiting millions of events. To preliminarily predict the mainstream public reaction to these events, we study trendy response prediction to automatically generate top-liked user replies to social media events. While previous works focus on generating responses without factoring in popularity, we propose Popularity-Aligned Language Models (PopALM) to distinguish responses liked by a larger audience through reinforcement learning. Recognizing the noisy labels from user "likes", we tailor-make curriculum learning in proximal policy optimization (PPO) to help models capture the essential samples for easy-to-hard training. In experiments, we build a large-scale Weibo dataset for trendy response prediction, and its results show that PopALM can help boost the performance of advanced language models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_18950 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PopALM: Popularity-Aligned Language Models for Social Media Trendy Response Prediction Yu, Erxin Li, Jing Xu, Chunpu Computation and Language Social media platforms are daily exhibiting millions of events. To preliminarily predict the mainstream public reaction to these events, we study trendy response prediction to automatically generate top-liked user replies to social media events. While previous works focus on generating responses without factoring in popularity, we propose Popularity-Aligned Language Models (PopALM) to distinguish responses liked by a larger audience through reinforcement learning. Recognizing the noisy labels from user "likes", we tailor-make curriculum learning in proximal policy optimization (PPO) to help models capture the essential samples for easy-to-hard training. In experiments, we build a large-scale Weibo dataset for trendy response prediction, and its results show that PopALM can help boost the performance of advanced language models. |
| title | PopALM: Popularity-Aligned Language Models for Social Media Trendy Response Prediction |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2402.18950 |