This study characterizes linguistic sophistication within university-based online courses using Learning Management Systems (LMS) across various academic disciplines. The research employs natural language processing tools to extract detailed linguistic features from student discussion posts and utilizes Principal Components Analysis (PCA) to identify distinct linguistic profiles. These profiles are analyzed to understand how linguistic sophistication varies across different educational contexts, specifically among various schools and courses. Subsequent cluster analysis reveals statistically significant distinct groups based on linguistic attributes. Despite the comprehensive analysis, the study did not establish significant predictive models linking linguistic sophistication to any direct educational outcomes. Instead, the findings highlight significant differences in language use across disciplines, suggesting that each academic field may have unique linguistic norms. The study emphasizes the need for further research to explore the underlying factors that influence these linguistic characteristics and their implications for educational practices.

The use of chatbots has become increasingly popular in the field of education. Hence, the quality of the prompts used by chatbots can greatly influence the quality of the generated responses which in tum contributes to desirable outcomes related to the overall learning experience. However, even as known criteria for efficient prompts are prevalent, there is a dearth of measurable and concrete linguistic factors that guide prompt engineering. This paper presents a composite score for ChatGPT prompts which can be made applicable to other foundational generative Al chatbots. Through a computational linguistic analysis of known efficient prompts used in learning, emergent linguistic factors point to the relationship of linguistic features and the confidence of ChatGPT responses to well-structured prompts that use the said linguistic features. The linguistic features are the average collostructural strength, collostructural ratio diversity, specificity, and academic language use. These features depict the quality of prompts that pertain to the grammatical structure, specificity, and relevance to the task at hand, and academic language use. Further, these features constitute a composite score for prompts introduced in this study that represent linguistic efficiency and subsequently, correlates to perplexity or certainty estimates of the generated responses of ChatGPT.

This study presents the results of a computational discourse analysis of discussion threads within an online Math tutoring platform. This work is theoretically motivated by prior work that established the importance of linguistic and semantic features in the discourse in mathematics education. The end goal of this study is to understand the characteristics of language that is produced and used within a discussion board for math. The discussion board corpus comprises of posts from 4,720 students, teachers, and study experts who interacted within an online teaching and learning tutoring platform for math. Linguistic profiles of the discussion board discourse were estimated using Principal Component Analysis (PCA) based on Coh-Metrix linguistic features related to cohesion, language sophistication, and lexical characteristics. The PCA analysis yielded seven Math Discourse Linguistic Components, which collectively explained 49% of the variance in the dataset. Theoretical and conceptual validation of components revealed that the linguistic features align with the communication goal and the nature of mathematics. The linguistic profiles that characterized the discussion board discourse included referential cohesion, information density, instructional language, lexical variation, compare and contrast devices, explicit relations devices, and syntactic complexity. The dominance of cohesive cues within the linguistic profiles demonstrate the communication goals within the Math discourse such as elaboration, providing instruction, compare and contrast, establishing explicit relations, and presenting information. As such, these components characterize the Math Discussion Board discourse in terms of variations in cohesive and task-oriented cues within communication among students.

We investigated the affective states (both individual and shared emotions) of students using a collaborative and educational game for English called Ibigkas! Our goal was two-fold: (1) To determine the incidence and persistence of affective states exhibited by the students when working individually and in groups, and (2) to adapt the Baker Rodrigo Ocumpaugh Monitoring Protocol for collaborative learning situations. Our findings for this study are as follows: (1) in single-player mode, students exhibited greater engaged concentration, pride, and frustration and less excitement, delight, and confusion compared to the multiplayer mode; (2) that individual emotions can be distinct from group emotions; (3) that negative emotions like frustration and blame/guilt were only felt at the individual level and were not observed as shared by all the members of the group; (4) affective states tended to persist more within an individualized game setting compared to the collaborative game setting where there was a greater number of opportunities to experience a wider range of emotions, hence the low chance of persistence; (5) students within an individualized setting spent more time solving the game rounds, had fewer incorrect answers, even as they experienced more frustration, and finally, (6) students within a collaborative setting had fewer errors when they had a higher incidence of excitement and had more errors when they appeared to be concentrating due to the presence of the “gaming the system” behavior.

This paper presents the testing and development of Learning Likha, an English language-based digital game for Filipino learners from 9- to 12-years old. The game focuses on the literacy skill of noting explicit details while incidentally learning about Filipino culture. In an in-vivo pilot test, we measured student comprehension and engagement. We found that the students who performed better and had greater confidence enjoyed using the software but were less engaged than those who performed more poorly.

This paper investigates the phenomenon of frustration when taken alone and when part of other affective sequences. The study attempted to determine the incidence of frustration and sequences involving frustration and their relationship with student achievement. 60 high school students from a university in the Philippines were asked to use Physics Playground for 120 minutes. Human observers recorded student cognitive affective states following BROMP while the game itself logged student activity. Frustration was found to have the second highest incidence from among the other affective states. Frustration, as well as sequences involving frustration, was found to be negatively correlated to student achievement occurring more than chance.

The goal of this paper was to examine affect-related factors and its relationship with student learning while tutoring an agent called SimStudent. These affect-related factors are the negativity of student self-explanations, the incidence and persistence of student affective states. Secondary school students who were part of this study were asked to teach their SimStudents solve algebra equations and make them pass all the quizzes. Results revealed that students failed to learn which led us to investigate other factors that could have attributed to this failure. Although the non-negatively valenced self-explanations did not have significant relationships with the students’ learning gains, the self-explanations were helpful in terms of mathematical content and they generally exhibited positive attitudes when giving the self-explanations. Students also tended to perform better with higher levels of good confusion. Higher levels of boredom were associated with poorer learning. Boredom and confusion were the most persistent but both did not have significant relationships with student learning. Though the negative correlations of the negative self-explanations, incidence and persistence of boredom vis-à-vis learning were not significant, the findings imply that negativity is linked to students’ poor performance.