Collaborative game-based learning offers opportunities for students to participate in small group learning experiences that foster knowledge sharing, problem solving, and engagement. Student satisfaction with their collaborative experiences plays a pivotal role in shaping positive learning outcomes and is a critical factor in group success during learning. Gauging students' satisfaction within collaborative learning contexts can offer insights into student engagement and participation levels while affording practitioners the ability to provide targeted interventions or scaffolding. In this paper, we propose a framework for inferring student collaboration satisfaction with multimodal learning analytics from collaborative interactions. Utilizing multimodal data collected from 50 middle school students engaged in collaborative game-based learning, we predict student collaboration satisfaction. We first evaluate the performance of baseline models on individual modalities for insight into which modalities are most informative. We then devise a multimodal deep learning model that leverages a cross-attention mechanism to attend to salient information across modalities to enhance collaboration satisfaction prediction. Finally, we conduct ablation and feature importance analysis to understand which combination of modalities and features is most effective. Findings indicate that various combinations of data sources are highly beneficial for student collaboration satisfaction prediction. [For the complete proceedings, see ED675485.]