Personalizing computer-based testing services to examinees can be improved by considering their behavioral models. This study aims to contribute towards deeper understanding the examinee's time spent and achievement behavior during testing according to the five personality traits by exploiting assessment analytics. Further, it aims to investigate assessment analytics appropriateness for classifying students and generating enhanced student models to guide personalization of testing services. In this study, the LAERS assessment environment and the Big Five Inventory were used to track the response times of 112 undergraduate students and to extract their personality traits respectively. Partial Least Squares was used to detect fundamental relationships between the collected data, and Supervised Learning Algorithms were used to classify students. Results indicate a positive effect of extraversion and agreeableness on goal-expectancy, a positive effect of conscientiousness on both goal-expectancy and level of certainty, and a negative effect of neuroticism and openness on level of certainty. Further, extraversion, agreeableness and conscientiousness have statistically significant indirect impact on students' response-times and level of achievement. Moreover, the ensemble RandomForest method provides accurate classification results, indicating that a time-spent driven description of students' behavior could have added value towards dynamically reshaping the respective models. Further implications of these findings are also discussed. (C) 2017 Elsevier Ltd. All rights reserved.
