SCRAG: Social Computing-Based Retrieval Augmented Generation for Community Response Forecasting in Social Media Environments
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912343837900800 |
|---|---|
| author | Sun, Dachun Lyu, You Li, Jinning Chen, Yizhuo Wang, Tianshi Kimura, Tomoyoshi Abdelzaher, Tarek |
| author_facet | Sun, Dachun Lyu, You Li, Jinning Chen, Yizhuo Wang, Tianshi Kimura, Tomoyoshi Abdelzaher, Tarek |
| contents | This paper introduces SCRAG, a prediction framework inspired by social computing, designed to forecast community responses to real or hypothetical social media posts. SCRAG can be used by public relations specialists (e.g., to craft messaging in ways that avoid unintended misinterpretations) or public figures and influencers (e.g., to anticipate social responses), among other applications related to public sentiment prediction, crisis management, and social what-if analysis. While large language models (LLMs) have achieved remarkable success in generating coherent and contextually rich text, their reliance on static training data and susceptibility to hallucinations limit their effectiveness at response forecasting in dynamic social media environments. SCRAG overcomes these challenges by integrating LLMs with a Retrieval-Augmented Generation (RAG) technique rooted in social computing. Specifically, our framework retrieves (i) historical responses from the target community to capture their ideological, semantic, and emotional makeup, and (ii) external knowledge from sources such as news articles to inject time-sensitive context. This information is then jointly used to forecast the responses of the target community to new posts or narratives. Extensive experiments across six scenarios on the X platform (formerly Twitter), tested with various embedding models and LLMs, demonstrate over 10% improvements on average in key evaluation metrics. A concrete example further shows its effectiveness in capturing diverse ideologies and nuances. Our work provides a social computing tool for applications where accurate and concrete insights into community responses are crucial. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_16947 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SCRAG: Social Computing-Based Retrieval Augmented Generation for Community Response Forecasting in Social Media Environments Sun, Dachun Lyu, You Li, Jinning Chen, Yizhuo Wang, Tianshi Kimura, Tomoyoshi Abdelzaher, Tarek Social and Information Networks Artificial Intelligence This paper introduces SCRAG, a prediction framework inspired by social computing, designed to forecast community responses to real or hypothetical social media posts. SCRAG can be used by public relations specialists (e.g., to craft messaging in ways that avoid unintended misinterpretations) or public figures and influencers (e.g., to anticipate social responses), among other applications related to public sentiment prediction, crisis management, and social what-if analysis. While large language models (LLMs) have achieved remarkable success in generating coherent and contextually rich text, their reliance on static training data and susceptibility to hallucinations limit their effectiveness at response forecasting in dynamic social media environments. SCRAG overcomes these challenges by integrating LLMs with a Retrieval-Augmented Generation (RAG) technique rooted in social computing. Specifically, our framework retrieves (i) historical responses from the target community to capture their ideological, semantic, and emotional makeup, and (ii) external knowledge from sources such as news articles to inject time-sensitive context. This information is then jointly used to forecast the responses of the target community to new posts or narratives. Extensive experiments across six scenarios on the X platform (formerly Twitter), tested with various embedding models and LLMs, demonstrate over 10% improvements on average in key evaluation metrics. A concrete example further shows its effectiveness in capturing diverse ideologies and nuances. Our work provides a social computing tool for applications where accurate and concrete insights into community responses are crucial. |
| title | SCRAG: Social Computing-Based Retrieval Augmented Generation for Community Response Forecasting in Social Media Environments |
| topic | Social and Information Networks Artificial Intelligence |
| url | https://arxiv.org/abs/2504.16947 |