{"slug": "belief-is-all-you-need-signed-belief-graph-neural-networks-for-topic-modeling-in", "title": "Belief Is All You Need: Signed Belief Graph Neural Networks for Topic Modeling in Conspiratorial Discourse", "summary": "Researchers developed a Signed Belief Graph Neural Network (SiBeGNN) to model conspiratorial discourse in Singapore-based Telegram groups, identifying seven topic clusters where conspiracy content appears across everyday discussions rather than isolated echo chambers. The method outperformed standard clustering approaches, achieving a cDBI of 8.38 versus 13.60–67.27, with 88% inter-rater agreement in cluster interpretation.", "body_md": "[Belief Is All You Need: Signed Belief Graph Neural Networks for Topic Modeling in Conspiratorial Discourse](https://aclanthology.org/2026.nlpcss-1.20.pdf)\n\n[Soorya Ram Shimgekar](/people/soorya-ram-shimgekar/),\n[Abhay Goyal](/people/abhay-goyal/unverified/),\n[Roy Ka-Wei Lee](/people/roy-ka-wei-lee/),\n[Koustuv Saha](/people/koustuv-saha/),\n[Pi Zonooz](/people/pi-zonooz/unverified/),\n[Edson C Tandoc Jr](/people/edson-c-tandoc-jr/unverified/),\n[Navin Kumar](/people/navin-kumar/unverified/)\n\n##### Abstract\n\nConspiratorial discourse is increasingly present in online communication, yet how it is organized across discussion topics remains unclear. We analyze Singapore-based Telegram groups to examine how conspiratorial content appears within everyday conversations rather than isolated echo chambers. To better capture the structure of such discussions, we propose a two-stage framework for topic modeling tailored to conspiratorial posts. First, a RoBERTa-large classifier identifies conspiratorial messages (F1 = 0.866) using 2,000 expert-annotated examples. We then construct a graph where connections reflect textual similarity and conspiratorial stance. This graph is modeled using a Signed Belief Graph Neural Network (SiBeGNN), which learns message embeddings that distinguish conspiratorial from non-conspiratorial content. We apply hierarchical clustering on these embeddings to perform topic modeling over 553,648 Telegram messages, producing seven topic clusters: General Legal Topics, Medical Concerns, Media Discussions, Banking and Finance, Contradictions in Authority, Group Moderation, and General Discussions. Our method substantially outperforms standard embedding-based clustering approaches (cDBI = 8.38 vs. 13.60–67.27), with manual evaluation showing 88% inter-rater agreement in cluster interpretation. The results show that conspiratorial content appears across multiple everyday topics, including finance, law, and daily life, rather than forming isolated thematic communities.- Anthology ID:\n- 2026.nlpcss-1.20\n- Volume:\n[Proceedings of the Seventh Workshop on Natural Language Processing and Computational Social Science](/volumes/2026.nlpcss-1/)- Month:\n- July\n- Year:\n- 2026\n- Address:\n- San Diego\n- Editors:\n[Dallas Card](/people/dallas-card/),[Anjalie Field](/people/anjalie-field/),[Katherine Keith](/people/katherine-keith/),[Julia Mendelsohn](/people/julia-mendelsohn/)- Venues:\n[NLP+CSS](/venues/nlpcss/)|[WS](/venues/ws/)- SIG:\n- Publisher:\n- Association for Computational Linguistics\n- Note:\n- Pages:\n- 341–355\n- Language:\n- URL:\n[https://aclanthology.org/2026.nlpcss-1.20/](https://aclanthology.org/2026.nlpcss-1.20/)- DOI:\n- Cite (ACL):\n- Soorya Ram Shimgekar, Abhay Goyal, Roy Ka-Wei Lee, Koustuv Saha, Pi Zonooz, Edson C Tandoc Jr, and Navin Kumar. 2026.\n[Belief Is All You Need: Signed Belief Graph Neural Networks for Topic Modeling in Conspiratorial Discourse](https://aclanthology.org/2026.nlpcss-1.20/). In*Proceedings of the Seventh Workshop on Natural Language Processing and Computational Social Science*, pages 341–355, San Diego. Association for Computational Linguistics. - Cite (Informal):\n[Belief Is All You Need: Signed Belief Graph Neural Networks for Topic Modeling in Conspiratorial Discourse](https://aclanthology.org/2026.nlpcss-1.20/)(Shimgekar et al., NLP+CSS 2026)- PDF:\n[https://aclanthology.org/2026.nlpcss-1.20.pdf](https://aclanthology.org/2026.nlpcss-1.20.pdf)", "url": "https://wpnews.pro/news/belief-is-all-you-need-signed-belief-graph-neural-networks-for-topic-modeling-in", "canonical_source": "https://aclanthology.org/2026.nlpcss-1.20/", "published_at": "2026-07-13 00:00:00+00:00", "updated_at": "2026-07-13 21:42:40.894151+00:00", "lang": "en", "topics": ["natural-language-processing", "machine-learning", "artificial-intelligence"], "entities": ["Soorya Ram Shimgekar", "Abhay Goyal", "Roy Ka-Wei Lee", "Koustuv Saha", "Pi Zonooz", "Edson C Tandoc Jr", "Navin Kumar", "Telegram"], "alternates": {"html": "https://wpnews.pro/news/belief-is-all-you-need-signed-belief-graph-neural-networks-for-topic-modeling-in", "markdown": "https://wpnews.pro/news/belief-is-all-you-need-signed-belief-graph-neural-networks-for-topic-modeling-in.md", "text": "https://wpnews.pro/news/belief-is-all-you-need-signed-belief-graph-neural-networks-for-topic-modeling-in.txt", "jsonld": "https://wpnews.pro/news/belief-is-all-you-need-signed-belief-graph-neural-networks-for-topic-modeling-in.jsonld"}}