Abstract:

Self-control ability (self-control) is an important ability for individuals to adapt to society and achieve life goals. However, the task experiments and scales commonly used in psychology need to consume a lot of time and human resources. At the same time, the subjective consciousness of the research object will affect the confidence of the evaluation results. This paper proposes a self-control evaluation method based on LSTM model. The method uses the behavior data of college students on campus as the data source, and uses the LSTM model to extract the time series characteristics of the behavior data. On the test set, the correlation coefficient between the evaluation result and the psychological scale method measurement result is 0.66, and the method can eliminate the subjective influence of the research object. It is suitable for large-scale student self-control evaluation in schools and has important application prospects.

Key words: self-control, behavioral data, deep learning, LSTM