This study investigates how individual differences related to creative and verbal fluencies can be differentiated and modelled through the linguistic features that manifest in student writing. Using computational linguistics, we analyzed samples of intrapersonal writing to extract linguistic features that align to specific dimensions of language. Creative fluency scores were calculated based on the number of unique ideas generated during the Alternate Uses Task (AUT); verbal fluency scores were calculated based on the number of unique semantic categories produced during the animal naming task. We then developed machine learning models to predict creative and verbal fluency scores based on the linguistic features of participant essays. Results indicate that creative fluency is more strongly predicted by linguistic features (particularly descriptive and cohesion indices) than verbal fluency. Key predictors of creative fluency include features that capture lexical diversity and the global connectedness of ideas. Importantly, our results align with theoretical frameworks related to convergent and divergent thinking. Findings highlight the potential for leveraging learning analytics to offer new insights into complex cognitive processes such as creativity. Implications for stealth assessments and personalized feedback within automated writing systems are discussed as paths for future research.