Unlocking Insights in Educational Process Data With a Sequential Reservoir Method

• In Event: AERA Roundtable Session Friday 9:50 am Four Seasons Ballroom 4
  In Roundtable Session: Machine Learning Techniques I: Advancing Equity, Prediction, and Measurement (Table 4)

Abstract

Process data, recorded in computer log files, capture the sequence of examinees' response activities, for example, timestamped keystrokes, during the educational assessment. Traditional measurement methods are often inadequate for handling this type of data. In this paper, we proposed a sequential reservoir method based on echo state network, particle swarm optimization, and singular value decomposition. This method has been evaluated using both simulated and empirical data. Results suggested that, on one hand, the model effectively transforms action sequences into standardized and meaningful features, and on the other hand, these features are instrumental in categorizing latent behavioral groups and predicting latent information, offering comprehensive information insights into examinees' assessment behaviors, such as action sequence lengths.

Authors

• Jiawei Xiong, Curriculum Associates

• Qidi Liu, GlobalFoundries

• Cheng Tang, University of Georgia