A key untapped feature of game-based learning environments is their capacity to generate a rich stream of fine-grained learning interaction data. The learning behaviors captured in these data provide a wealth of information on student learning, which stealth assessment can utilize to unobtrusively draw inferences about student knowledge to provide tailored problem-solving support. In this paper, we present a long short-term memory network (LSTM)-based stealth assessment framework that takes as input an observed sequence of raw game-based learning environment interaction data along with external pre-learning measures to infer students’ post-competencies. The framework is evaluated using data collected from 191 middle school students interacting with a game-based learning environment for middle grade computational thinking. Results indicate that LSTM-based stealth assessors induced from student game-based learning interaction data outperform comparable models that required labor-intensive hand-engineering of input features. The findings suggest that the LSTM-based approach holds significant promise for evidence modeling in stealth assessment.
more »
« less
Improving Stealth Assessment in Game-Based Learning with LSTM-Based Analytics
A key affordance of game-based learning environments is their potential to unobtrusively assess student learning without interfering with gameplay. In this paper, we introduce a temporal analytics framework for stealth assessment that analyzes students' problem-solving strategies. The strategy-based temporal analytic framework uses long short-term memory network-based evidence models and clusters sequences of students' problem-solving behaviors across consecutive tasks. We investigate this strategy based temporal analytics framework on a dataset of problem solving behaviors collected from student interactions with a game-based learning environment for middle school computational thinking. The results of an evaluation indicate that the strategy-based temporal analytics framework significantly outperforms competitive baseline models with respect to stealth assessment predictive accuracy.
more »
« less
- NSF-PAR ID:
- 10100664
- Date Published:
- Journal Name:
- International Conference on Educational Data Mining
- Page Range / eLocation ID:
- 208 - 218
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Abstract This exploratory paper highlights how problem‐based learning (PBL) provided the pedagogical framework used to design and interpret learning analytics from C
rystal Island: EcoJourneys , a collaborative game‐based learning environment centred on supporting science inquiry. In Crystal Island: EcoJourneys , students work in teams of four, investigate the problem individually and then utilize a brainstorming board, an in‐game PBL whiteboard that structured the collaborative inquiry process. The paper addresses a central question: how can PBL support the interpretation of the observed patterns in individual actions and collaborative interactions in the collaborative game‐based learning environment? Drawing on a mixed method approach, we first analyzed students' pre‐ and post‐test results to determine if there were learning gains. We then used principal component analysis (PCA) to describe the patterns in game interaction data and clustered students based on the PCA. Based on the pre‐ and post‐test results and PCA clusters, we used interaction analysis to understand how collaborative interactions unfolded across selected groups. Results showed that students learned the targeted content after engaging with the game‐based learning environment. Clusters based on the PCA revealed four main ways of engaging in the game‐based learning environment: students engaged in low to moderate self‐directed actions with (1) high and (2) moderate collaborative sense‐making actions, (3) low self‐directed with low collaborative sense‐making actions and (4) high self‐directed actions with low collaborative sense‐making actions. Qualitative interaction analysis revealed that a key difference among four groups in each cluster was the nature of verbal student discourse: students in the low to moderate self‐directed and high collaborative sense‐making cluster actively initiated discussions and integrated information they learned to the problem, whereas students in the other clusters required more support. These findings have implications for designing adaptive support that responds to students' interactions with in‐game activities.Practitioner notes What is already known about this topic
Learning analytic methods have been effective for understanding student learning interactions for the purposes of assessment, profiling student behaviour and the effectiveness of interventions.
However, the interpretation of analytics from these diverse data sets are not always grounded in theory and challenges of interpreting student data are further compounded in collaborative inquiry settings, where students work in groups to solve a problem.
What this paper adds
Problem‐based learning as a pedagogical framework allowed for the design to focus on individual and collaborative actions in a game‐based learning environment and, in turn, informed the interpretation of game‐based analytics as it relates to student's self‐directed learning in their individual investigations and collaborative inquiry discussions.
The combination of principal component analysis and qualitative interaction analysis was critical in understanding the nuances of student collaborative inquiry.
Implications for practice and/or policy
Self‐directed actions in individual investigations are critical steps to collaborative inquiry. However, students may need to be encouraged to engage in these actions.
Clustering student data can inform which scaffolds can be delivered to support both self‐directed learning and collaborative inquiry interactions.
All students can engage in knowledge‐integration discourse, but some students may need more direct support from teachers to achieve this.
-
Previous studies have convincingly shown that traditional, content-centered, and didactic teaching methods are not effective for developing a deep understanding and knowledge transfer. Nor does it adequately address the development of critical problem-solving skills. Active and collaborative instruction, coupled with effective means to encourage student engagement, invariably leads to better student learning outcomes irrespective of academic discipline. Despite these findings, the existing construction engineering programs, for the most part, consist of a series of fragmented courses that mainly focus on procedural skills rather than on the fundamental and conceptual knowledge that helps students become innovative problem-solvers. In addition, these courses are heavily dependent on traditional lecture-based teaching methods focused on well-structured and closed-ended problems that prepare students to plug variables into equations to get the answer. Existing programs rarely offer a systematic approach to allow students to develop a deep understanding of the engineering core concepts and discover systematic solutions for fundamental problems. Without properly understanding these core concepts, contextualized in domain-specific settings, students are not able to develop a holistic view that will help them to recognize the big picture and think outside the box to come up with creative solutions for arising problems. The long history of empirical learning in the field of construction engineering shows the significant potential of cognitive development through direct experience and reflection on what works in particular situations. Of course, the complex nature of the construction industry in the twenty-first century cannot afford an education through trial and error in the real environment. However, recent advances in computer science can help educators develop virtual environments and gamification platforms that allow students to explore various scenarios and learn from their experiences. This study aims to address this need by assessing the effectiveness of guided active exploration in a digital game environment on students’ ability to discover systematic solutions for fundamental problems in construction engineering. To address this objective, through a research project funded by the NSF Division of Engineering Education and Centers (EEC), we designed and developed a scenario-based interactive digital game, called Zebel, to guide students solve fundamental problems in construction scheduling. The proposed gamified pedagogical approach was designed based on the Constructivism learning theory and a framework that consists of six essential elements: (1) modeling; (2) reflection; (3) strategy formation; (4) scaffolded exploration; (5) debriefing; and (6) articulation. We also designed a series of pre- and post-assessment instruments for empirical data collection to assess the effectiveness of the proposed approach. The proposed gamified method was implemented in a graduate-level construction planning and scheduling course. The outcomes indicated that students with no prior knowledge of construction scheduling methods were able to discover systematic solutions for fundamental scheduling problems through their experience with the proposed gamified learning method.more » « less
-
Prediction of student performance in Introductory programming courses can assist struggling students and improve their persistence. On the other hand, it is important for the prediction to be transparent for the instructor and students to effectively utilize the results of this prediction. Explainable Machine Learning models can effectively help students and instructors gain insights into students’ different programming behaviors and problem-solving strategies that can lead to good or poor performance. This study develops an explainable model that predicts students’ performance based on programming assignment submission information. We extract different data-driven features from students’ programming submissions and employ a stacked ensemble model to predict students’ final exam grades. We use SHAP, a game-theory-based framework, to explain the model’s predictions to help the stakeholders understand the impact of different programming behaviors on students’ success. Moreover, we analyze the impact of important features and utilize a combination of descriptive statistics and mixture models to identify different profiles of students based on their problem-solving patterns to bolster explainability. The experimental results suggest that our model significantly outperforms other Machine Learning models, including KNN, SVM, XGBoost, Bagging, Boosting, and Linear regression. Our explainable and transparent model can help explain students’ common problem-solving patterns in relationship with their level of expertise resulting in effective intervention and adaptive support to students.more » « less
-
more » « less
Abstract In this study, we investigated the validity of a stealth assessment of physics understanding in an educational game, as well as the effectiveness of different game‐level delivery methods and various in‐game supports on learning. Using a game called
Physics Playground , we randomly assigned 263 ninth‐ to eleventh‐grade students into four groups: adaptive, linear, free choice and no‐treatment control. Each condition had access to the same in‐game learning supports during gameplay. Results showed that: (a) the stealth assessment estimates of physics understanding were valid—significantly correlating with the external physics test scores; (b) there was no significant effect of game‐level delivery method on students' learning; and (c) physics animations were the most effective (among eight supports tested) in predicting both learning outcome and in‐game performance (e.g. number of game levels solved). We included student enjoyment, gender and ethnicity in our analyses as moderators to further investigate the research questions.
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
