Cixiao Wang

Jianjun Xiao, Cixiao Wang, Wenmei Zhang

Measuring collaborative problem solving (CPS) synergy remains challenging in learning analytics, as classical manual coding cannot capture emergent system-level dynamics. This study introduces a computational framework that integrates automated discourse analysis with the Synergy Degree Model (SDM) to quantify CPS synergy from group communication. Data were collected from 52 learners in 12 groups during a 5-week connectivist MOOC (cMOOC) activity. Nine classification models were applied to automatically identify ten CPS behaviors across four interaction levels: operation, wayfinding, sense-making, and creation. While BERT achieved the highest accuracy, GPT models demonstrated superior precision suitable for human-AI collaborative coding. Within the SDM framework, each interaction level was treated as a subsystem to compute group-level order parameters and derive synergy degrees. Permutation tests showed automated measures preserve construct validity, despite systematic biases at the subsystem level. Statistical analyses revealed significant task-type differences: survey study groups exhibited higher creation-order than mode study groups, suggesting "controlled disorder" may benefit complex problem solving. Importantly, synergy degree distinguished collaborative quality, ranging from excellent to failing groups. Findings establish synergy degree as a sensitive indicator of collaboration and demonstrate the feasibility of scaling fine-grained CPS analytics through AI-in-the-loop approaches.

Jianjun Xiao, Cixiao Wang

Connectivist MOOCs (cMOOCs) rely on learner-driven interaction, yet their intentionally light facilitation makes it difficult to design generative AI participation that is both scalable and educationally productive. This design-based research study examined how human-AI interaction can be designed for discussion facilitation through a collaborative AI-in-the-loop workflow. Across two iterations in a five-week cMOOC (N = 606), we designed, deployed, and evaluated a facilitation system that combined network-structure-driven target selection, discourse-adaptive response roles, and mandatory human review before AI participation became visible in the community. Iteration 1 (Weeks 1-2) focused on refining the interaction design, showing that the most sustainable facilitation patterns were Guide (70.4%) and Amplifier (28.5%) responses and yielding explicit moderation standards for publishable AI participation. Iteration 2 (Weeks 3-5) examined how different forms of AI-mediated interaction related to social and cognitive presence. AI participation selectively enhanced Open Communication (r = 0.188, p = 0.006), Networked Cohesion (r = 0.274, p < 0.001), and overall social presence (r = 0.162, p = 0.015), while cognitive presence showed no overall improvement. More importantly, direct learner-agent interaction was associated with significantly higher social presence (r = 0.186, p = 0.004) and higher-order cognitive indicators-Integration (r = 0.206, p = 0.001) and Resolution/Creation (r = 0.350, p < 0.001)-than mere co-presence in AI-involved threads. The findings suggest that effective GenAI-supported discussion depends less on AI presence alone than on interaction design: reciprocal exchange, discourse-adaptive facilitation roles, and collaborative human review appear to be key conditions for productive AI participation in online learning communities.