Online asynchronous interaction is considered a core part of online teacher training, which has an important impact on learners' learning experience and learning outcomes. How to provide immediate and effective feedback through technical support based on the learners' interactive content and enhance interactive connection has become a key issue in massive online teacher training. This study designed an automated feedback framework from feedback strategy, feedback way, and feedback type. Then, we designed an emotional-cognitive feedback approach and an emotional-cognitive-metacognitive feedback approach based on automated analysis of online asynchronous interactions. A massive online teacher training course was conducted to provide automated feedback to 1438 learners in the online asynchronous interaction. Results showed that the two approaches enabled learners to interact more positively, slow down the growth of the dropout rate, and help learners adjust their emotional state and cognitive level. Particularly, the emotional-cognitive-metacognitive feedback approach could facilitate learners' self-regulation and improve feedback quality. Through questionnaires and semi-structured interviews, we found that learners were obsessed by automated emotional-cognitive-metacognitive feedback approach and they believed that it was helpful for their learning. This study is of great significance and application value to widely carry out high-quality, massive and personalized online learning.