Artificial Intelligence and Civil Discourse: How LLMs Moderate Climate Change Conversations
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916793826672640 |
|---|---|
| author | Fan, Wenlu Xu, Wentao |
| author_facet | Fan, Wenlu Xu, Wentao |
| contents | As large language models (LLMs) become increasingly integrated into online platforms and digital communication spaces, their potential to influence public discourse - particularly in contentious areas like climate change - requires systematic investigation. This study examines how LLMs naturally moderate climate change conversations through their distinct communicative behaviors. We conduct a comparative analysis of conversations between LLMs and human users on social media platforms, using five advanced models: three open-source LLMs (Gemma, Llama 3, and Llama 3.3) and two commercial systems (GPT-4o by OpenAI and Claude 3.5 by Anthropic). Through sentiment analysis, we assess the emotional characteristics of responses from both LLMs and humans. The results reveal two key mechanisms through which LLMs moderate discourse: first, LLMs consistently display emotional neutrality, showing far less polarized sentiment than human users. Second, LLMs maintain lower emotional intensity across contexts, creating a stabilizing effect in conversations. These findings suggest that LLMs possess inherent moderating capacities that could improve the quality of public discourse on controversial topics. This research enhances our understanding of how AI might support more civil and constructive climate change discussions and informs the design of AI-assisted communication tools. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_12077 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Artificial Intelligence and Civil Discourse: How LLMs Moderate Climate Change Conversations Fan, Wenlu Xu, Wentao Computers and Society Computation and Language As large language models (LLMs) become increasingly integrated into online platforms and digital communication spaces, their potential to influence public discourse - particularly in contentious areas like climate change - requires systematic investigation. This study examines how LLMs naturally moderate climate change conversations through their distinct communicative behaviors. We conduct a comparative analysis of conversations between LLMs and human users on social media platforms, using five advanced models: three open-source LLMs (Gemma, Llama 3, and Llama 3.3) and two commercial systems (GPT-4o by OpenAI and Claude 3.5 by Anthropic). Through sentiment analysis, we assess the emotional characteristics of responses from both LLMs and humans. The results reveal two key mechanisms through which LLMs moderate discourse: first, LLMs consistently display emotional neutrality, showing far less polarized sentiment than human users. Second, LLMs maintain lower emotional intensity across contexts, creating a stabilizing effect in conversations. These findings suggest that LLMs possess inherent moderating capacities that could improve the quality of public discourse on controversial topics. This research enhances our understanding of how AI might support more civil and constructive climate change discussions and informs the design of AI-assisted communication tools. |
| title | Artificial Intelligence and Civil Discourse: How LLMs Moderate Climate Change Conversations |
| topic | Computers and Society Computation and Language |
| url | https://arxiv.org/abs/2506.12077 |