The interactive learning is a continuous process, which is full of a large number of learning interaction activities. The data generated between learners and learning interaction activities can reflect the online learning behaviors. Through the correlation analysis among learning interaction activities, this paper discusses the potential association rules, defines the data structures, mines the frequent item sets, and designs appropriate algorithms, then recommend learning decision makings based on association rules. The research methods and conclusions can provide feasible educational decision makings for the realization of personalization, probability prediction and decision feedback, which will improve the interactive learning environment, the algorithms, methods and modes designed in this paper are useful supplements for learning analytics.

Interactive learning environments can generate massive learning behavior data and the support of learning behavior big data can ensure the completeness of data analysis and robustness of relationship verification. In this study, learning behaviors are divided into training set and testing set, BP neural network and recurrent Elman network are integrated. Through the training set, the recursive multi-layer feedback neural network model based on the fusion of context features is constructed. The recognition algorithm is designed. From relative standard deviation (RSD) and prediction accuracy (P.A), the model and algorithm designed in this study are more suitable for the recognition and prediction of learning behavior data. Furthermore, the key topological path and interaction process equation of learning behaviors are designed, three kinds of intervention optimization strategies are constructed to serve the daily teaching processes of three courses. After two semesters of learning behavior feature recognition and relationship analysis, learners’ interest, assessment pass rate, or excellence rate have improved significantly. So the intervention optimization strategies of learning behaviors based on the analysis results of models and algorithms can influence the feature distribution and behavior trend.

The temporal sequence of learning behavior is multidimensional and continuous in MOOCs. On the one hand, it supports personalized learning methods, achieves flexible time and space. On the other hand, it also makes MOOCs produce a large number of dropouts and incomplete learning behaviors. Dropout prediction and decision feedback have become an important issue of MOOCs. This study carries out sufficient method design and decision analysis on the dropout trend. Based on a large number of learning behavior instances, we construct a multi behavior type association framework, design dropout prediction model to analyze the temporal sequence of learning behavior, then discuss the corresponding intervention measures, in order to provide adaptive monitoring mechanism for long-term tracking and short-term learning method selection, and enable adaptive decision feedback. the full experiment shows that the designed model might improve the performance of the dropout prediction, which achieves the reliability and feasibility. The whole research can provide key technical solution and decision, which has important theoretical and practical value for dropout research of MOOCs.

With the full application of MOOCs online learning, STEM multidisciplinary and knowledge structures have been achieved, but it has also resulted in a massive number of dropouts, seriously affected the learning sustainability of STEM education concepts, and made it difficult to achieve learning effectiveness. Based on the massive STEM learning behavior instances generated by MOOCs, as well as the entire learning periods, this study considers some key explicit and implicit features associated with learning behavior, and achieves the fusion of convolutional neural network and recurrent neural network through data-driven approaches, incorporates long short-term memory mechanism to develop dropout prediction methods and models. Based on the experimental results, we also discuss the relevant problems of dropouts related to STEM learning behavior, explore the key dropout temporal sequences of the learning process, identify related factors that have key impacts on learning behavior, and deduce intervention measures and early warning suggestions. The entire study can provide effective methods and decisions for researching the STEM learning behavior of MOOCs and has strong research feasibility and urgency.