arXiv:2509.16835v2 Announce Type: replace 
Abstract: Virtual brainstorming sessions have become a central component of collaborative problem solving, yet the large volume and uneven distribution of ideas often make it difficult to extract valuable insights efficiently. Manual coding of ideas is time-consuming and subjective, underscoring the need for automated approaches to support the evaluation of group creativity. In this study, we propose a semantic-driven topic modeling framework that integrates four modular components: transformer-based embeddings (Sentence-BERT), dimensionality reduction (UMAP), clustering (HDBSCAN), and topic extraction with refinement. The framework captures semantic similarity at the sentence level, enabling the discovery of coherent themes from brainstorming transcripts while filtering noise and identifying outliers. We evaluate our approach on structured Zoom brainstorming sessions involving student groups tasked with improving their university. Results demonstrate that our model achieves higher topic coherence compared to established methods such as LDA, ETM, and BERTopic, with an average coherence score of 0.687 (CV), outperforming baselines by a significant margin. Beyond improved performance, the model provides interpretable insights into the depth and diversity of topics explored, supporting both convergent and divergent dimensions of group creativity. This work highlights the potential of embedding-based topic modeling for analyzing collaborative ideation and contributes an efficient and scalable framework for studying creativity in synchronous virtual meetings.

تقدم دراسة جديدة إطارًا لنمذجة الموضوعات مدفوعًا بالمعنى مصممًا لتحسين تحليل الإبداع في جلسات العصف الذهني الافتراضية. يدمج هذا الإطار تقنيات متقدمة مثل تمثيلات Sentence-BERT، وUMAP لتقليل الأبعاد، وHDBSCAN للتجميع، واستخراج الموضوعات مع التكرير لتحديد الموضوعات المتماسكة بكفاءة من نصوص العصف الذهني.

Un nuevo estudio presenta un marco de modelado de temas impulsado por la semántica diseñado para mejorar el análisis de la creatividad en sesiones de lluvia de ideas virtuales. Este marco integra técnicas avanzadas como los embeddings de Sentence-BERT, UMAP para la reducción de dimensionalidad, clustering HDBSCAN y extracción de temas refinada para identificar de manera eficiente temas coherentes a partir de las transcripciones de lluvia de ideas.

Une nouvelle étude présente un cadre de modélisation de sujet axé sur la sémantique, conçu pour améliorer l'analyse de la créativité lors des sessions de brainstorming virtuel. Ce cadre intègre des techniques avancées telles que les embeddings Sentence-BERT, UMAP pour la réduction de dimensionnalité, le clustering HDBSCAN et l'extraction de sujets affinée pour identifier efficacement des thèmes cohérents à partir des transcriptions de brainstorming.

A new study presents a semantic-driven topic modeling framework designed to enhance the analysis of creativity in virtual brainstorming sessions. This framework integrates advanced techniques such as Sentence-BERT embeddings, UMAP for dimensionality reduction, HDBSCAN clustering, and refined topic extraction to efficiently identify coherent themes from brainstorming transcripts.

Semantic-Driven Topic Modeling for Analyzing Creativity in Virtual Brainstorming

One More Thing in AI – Your Shortcut to AI Mastery

Semantic-Driven Topic Modeling for Analyzing Creativity in Virtual Brainstorming

More coverage on this story

AgriLens: Semantic Retrieval in Agricultural Texts Using Topic Modeling and Language Models

Useful picks

One More Thing in AI

CoSpaceGPT

Metaflow AI

Earmark

TESSR

Semantic Pen