=Paper=
{{Paper
|id=Vol-2902/paper9
|storemode=property
|title=Multimodal Multi-Task Stealth Assessment for Reflection-Enriched Game-Based Learning
|pdfUrl=https://ceur-ws.org/Vol-2902/paper9.pdf
|volume=Vol-2902
|authors=Anisha Gupta,Dan Carpenter,Wookhee Min,Jonathan Rowe,Roger Azevedo,James Lester
|dblpUrl=https://dblp.org/rec/conf/aied/GuptaCMRAL21
}}
==Multimodal Multi-Task Stealth Assessment for Reflection-Enriched Game-Based Learning==
https://ceur-ws.org/Vol-2902/paper9.pdf
Multimodal Multi-Task Stealth Assessment for
Reflection-Enriched Game-Based Learning
Anisha Gupta1, Dan Carpenter1, Wookhee Min1, Jonathan Rowe1, Roger Azevedo2,
and James Lester1
1
North Carolina State University, Raleigh, NC 27695, USA
{agupta44, dcarpen2, wmin, jprowe, lester}@ncsu.edu
2
University of Central Florida, Orlando, FL 32816, USA
roger.azevedo@ucf.edu
Abstract. Game-based learning environments enable effective and engaging
learning experiences that can be dynamically tailored to students. There is grow-
ing interest in the role of reflection in supporting student learning in game-based
learning environments. By prompting students to periodically stop and reflect on
their learning processes, it is possible to gain insight into students’ perceptions
of their knowledge and problem-solving progress, which can in turn inform adap-
tive scaffolding to improve student learning outcomes. Given the positive rela-
tionship between student reflection and learning, we investigate the benefits of
jointly modeling post-test score and reflection depth using a multimodal, multi-
task stealth assessment framework. Specifically, we present a gated recurrent
unit-based multi-task stealth assessment framework that takes as input multi-
modal data streams (e.g., game trace logs, pre-test data, natural language re-
sponses to in-game reflection prompts) to jointly predict post-test scores and writ-
ten reflection depth scores. Evaluation results demonstrate that the multimodal
multi-task model outperforms single-task neural models that utilize subsets of the
modalities, as well as non-neural baselines such as random forest regressors. Our
multi-task stealth assessment framework for measuring students’ content
knowledge and reflection depth during game-based learning shows significant
promise for supporting student learning and improved reflection.
Keywords: Multimodal learning analytics, multi-task learning, natural lan-
guage processing, reflection, game-based learning
1 Introduction
Recent years have witnessed growing interest in game-based learning environments
due to their potential to foster student learning and create personalized learning experi-
ences [1-3]. By embedding story-based problems within interactive virtual environ-
ments, game-based learning environments can promote student interest and provide en-
gaging opportunities for problem solving. An important factor in game-based learning
environments is students’ ability to self-regulate their learning processes [4, 5]. Game-
Copyright © 2021 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
2
based learning environments with robust student performance assessment capabilities
show significant promise for identifying gaps in student knowledge and informing
adaptive scaffolding designed to support self-regulated learning and problem solving.
A key challenge is how to reliably model student knowledge without disrupting en-
gagement during learning activities. Stealth assessment addresses this challenge by an-
alyzing fine-grained sequences of game interaction data to automatically infer students'
knowledge and learning competencies without disrupting students’ game-based learn-
ing experiences [6, 7]. Following an evidence-centered assessment approach [8], stealth
assessment can be formulated as a regression task to predict students’ post-test scores
based on the observed sequences of students' problem-solving interactions during
game-based learning. Accurate predictions of post-test scores could inform instructors
about students in need of help. The predictions can also be utilized in-game to provide
scaffolds to dynamically remediate gaps in knowledge and support problem solving.
While in-game action sequences have been investigated as a traditional source of
predictive features for stealth assessment [7], students’ written reflections also hold
significant potential to improve prediction of student competencies when combined
with in-game action sequences [5]. Moreover, supporting effective reflection is itself
an important goal in game-based learning due to its central role in self-regulated learn-
ing. To identify whether students are reflecting effectively, reflections are often evalu-
ated in terms of their depth (e.g., non-reflective, slightly reflective, and highly reflective
[9]). However, analyzing written reflections is typically a manual process that is time
and resource-intensive, so a key question is how to automatically model student written
responses in order for stealth assessors to make robust predictions of learning outcomes.
This paper presents a multimodal multi-task machine learning framework for stealth
assessment that involves generating sequential predictions of students’ post-test and
reflection depth scores based upon students’ pre-test scores, game trace logs, and writ-
ten reflections. The multimodal multi-task stealth assessment models utilize features
extracted from students’ game trace logs, including in-game events and dynamically
changing learning goals, as well as linguistic features extracted from written reflections
using a pre-trained ELMo language model based on a stacked bidirectional recurrent
neural network [10]. We train stealth assessment models based on gated recurrent unit
(GRU) neural architectures [11] that employ hybrid fusion to model multimodal data
consisting of game trace logs and written reflection responses. We evaluate the predic-
tive performance of multimodal, multi-task stealth assessment models against a random
forest regressor as well as variants of unimodal and single-task GRU models.
2 Related Work
Multimodal machine learning techniques leverage information obtained across multiple
data channels and have been found to show improvement in predictive performance as
compared to unimodal models across a range of tasks [12]. These techniques have been
widely investigated for a range of learning environments in the context of multimodal
learning analytics [13, 14]. Aslan et al. developed a real-time multimodal analytics
framework for measuring student engagement using appearance and context-based
3
features in an authentic classroom setting [15]. Emerson et al. analyzed multi-channel
data including gaze, facial expression, and posture for predicting learner engagement
in interactive museum exhibits [16, 17]. To effectively deal with heterogeneous streams
of data, various data fusion methods have been explored along with multimodal learn-
ing analytics approaches. Zheng et al. [18] categorized data fusion techniques as being
feature-based [19], stage-based [20] and semantic meaning-based [21]. Henderson et
al. used multimodal data fusion for affect detection in game-based learning environ-
ments exploring feature-level as well as decision-level multimodal data fusion ap-
proaches [22]. Their results demonstrate that different data fusion approaches are suited
to different affect detection tasks.
Another strand of related work is research on stealth assessment [6]. Stealth assess-
ment is an application of evidence-centered design (ECD) [8], an assessment design
framework that utilizes task-level evidence to infer learners’ competencies on higher-
level concepts in game-based learning environments. Stealth assessment often utilizes
game trace logs (e.g., sequence of events, locations visited) to model student
knowledge, skills, and abilities using machine learning techniques [7, 23]. A promising
approach for augmenting stealth assessment models is using data from student reflec-
tions [24]. Game-based learning environments can be designed to ask students to sub-
mit written reflections detailing what they have learnt and how their past experiences
might shape their future learning plans, providing an important source of evidence for
stealth assessment. Carpenter et al. analyzed students written reflections in a game-
based learning environment by rating students’ reflections on a continuous scale based
on their reflection depth [25]. They evaluated several machine learning techniques for
their predictive performance on reflection scores. They reported the best performance
using an SVM model utilizing ELMo embeddings. Geden et al. examined modeling
approaches for predicting students’ post-test scores using game-based features, pre-test
scores and word embedding representations of reflection responses [5]. Our work lev-
erages feature representations extracted from game interaction data and students’ writ-
ten reflections to predict a sequence of reflection scores and post-test scores cast as a
time-series regression task in the context of multi-task learning [26].
3 Dataset
In this work, we use data from a pair of classroom studies conducted in 2018 and 2019
with CRYSTAL ISLAND, a game-based learning environment for middle school microbi-
ology education [5, 25, 27]. The objective of the game is to find a disease that is spread-
ing among a group of scientists on a remote island research station. In the game, the
students explore the virtual environment, talk to non-player characters, read science
books, articles and posters, test objects in a virtual laboratory, and submit a final diag-
nosis to the camp nurse. In both studies, a 17-item microbiology content knowledge
pre-test (M = 6.78, SD = 2.75) was administered a week before the students first inter-
acted with the game. Prior to game-based learning activities, researchers briefly intro-
duced the students to the game, and then students interacted with the game until they
solved the mystery, or approximately 100 minutes of gameplay time had elapsed. As
4
students interacted with CRYSTAL ISLAND (Figure 1, left), their game trace logs and
written responses were recorded, providing a detailed account of each students’ actions
in the learning environment. After completion of the game, students completed a 17-
item microbiology content knowledge post-test (M = 7.36, SD = 3.36), among other
post-game measures. Our dataset consists of data from 119 students. Of these students,
51% identified as females, and their ages ranged from 13 to 14 (M = 13.6, SD = 0.51).
Fig. 1. (left) CRYSTAL ISLAND game-based learning environment, (right) In-game reflection
prompt.
While playing the game, students were prompted at several checkpoints (Figure 1,
right) to reflect on their progress in the game and state their plans moving forward. At
the end of the game, two additional prompts appeared, requiring students to detail their
approach towards solving the current problem and propose a way to solve a similar
problem in the future. Across all types of reflection, there were 729 written reflection
responses. The average length of a reflection response was approximately 20 words. A
rubric was formulated for evaluating the reflection depth of written responses on a scale
of 1 to 5 [25]. Two researchers individually rated the written responses following the
rubric, and the final reflection rating was calculated by averaging the rating values for
each written response (M = 2.41, SD = 0.86). An intraclass correlation of 0.669 was
achieved indicating moderate inter-rater reliability.
4 Stealth Assessment Frameworks
4.1 Data Representation and Preprocessing
This work focuses on two game trace log features: events and completed plot points.
We only consider 8 distinct game event types in CRYSTAL ISLAND—conversing with a
virtual character, reading books and articles, filling out the diagnosis worksheet, en-
countering a written response prompt, accomplishing a goal, reading a poster, testing a
virtual object, and submitting a diagnosis—and 20 distinct plot points, which are in-
game milestone events important to successfully completing the game. The event fea-
ture is a cumulative count vector, with each element representing the number of occur-
rences of a specific event from the start of the game. We apply the standard score (z-
score) for the count of each event in the event vector to standardize count-based repre-
sentations. The plot point vector is a binary representation with each element
5
representing a unique gameplay milestone, set to zero by default and changed to one
once the milestone is accomplished.
In addition to game trace log features, we also use ELMo embeddings [10] of stu-
dents’ written reflections. These written reflections are the responses provided by the
students to the in-game prompts. ELMo sentence embeddings have the benefit of en-
coding contextual information. We use an ELMo model pre-trained with the 1 Billion
Word Benchmark comprising approximately 800M tokens of news crawl data from
WMT 2011 [10]. We consider the average of the ELMo word embeddings in each of
the written responses to construct a single embedding of length 1,024 for each response.
Since the embedding size is prohibitively large to effectively model our dataset, we
reduce the dimensionality of the embeddings by applying principal component analysis
(PCA) and preserving the 32 features that have the most variance. In our stealth assess-
ment models, the most recent reflection embedding is passed as input, along with the
game trace logs, at each time step. For predictions prior to a student’s first reflection,
an embedding with uniform random noise is used to indicate that no information is yet
available. We also include students’ standardized pre-test scores as input to our models.
We subsample each student’s trace data into overlapping subsequences of 20 con-
secutive actions, such that each action taken by a student has a corresponding subse-
quence, comprising the current and past 19 actions. Both cumulative and binary vectors
in these subsequences are based on actions performed from the start of gameplay until
the current timestamp. The first few entries whose lengths are shorter than 20 are pad-
ded with zeros to keep the length of each subsequence to exactly 20 timesteps. The task
of predicting the series of reflection ratings is formulated as sequential inferences on
the rating of the next written response based on the current subsequence. We model our
problem as a regression task. For each in-game event, we predict the post-test score as
well as the reflection rating. The reflection rating label corresponds to the next written
response that the student is expected to submit at a later time step.
4.2 Modelling Techniques
In our current work, we experiment with early, late, and hybrid fusion of multimodal
data. We hypothesize that how to fuse different modalities plays a crucial role to obtain
high-fidelity predictive models, particularly because each modality has a different na-
ture, number of features, and representation method. We compare performance
achieved using the three data fusion techniques and identify the best performing tech-
nique for each task. Multi-task learning (MTL) allows a model to share intermediate
latent representations between related tasks, enabling the model to leverage information
across related tasks to achieve better generalization performance [26]. We evaluate
MTL focusing on whether shared representations for modeling related learning out-
comes of post-test scores and written reflection ratings can benefit predictive perfor-
mance for one or both tasks. For training each model, we used Adam optimizer [28]
with mean squared error (MSE) as the loss function. The models are detailed as follows:
Early fusion model. This model takes a concatenation of pretest scores, written reflec-
tion embeddings and game trace logs as input, which is then passed through a GRU
6
layer (128 hidden units, 0.1 dropout, 0.01 L2 kernel/recurrent/bias regularization fac-
tor), followed by a dense (64 units, ReLU activation) and a dropout layer (0.1). The
hidden representation is passed through a dense layer and a separate dense layer for
predicting post-test score and time-series reflection rating (each with 8 shared hidden
units followed by 1 output unit). (Please note that the following late and hybrid fusion
methods use the same hyperparameter configurations reported above.)
Late fusion model. This model takes written reflection embeddings and gameplay logs
as inputs through separate GRU layers followed by dense and dropout layers. Pre-test
scores are passed through a dense network. These three outputs are concatenated and
passed to two dense layers predicting post-test score and time-series reflection rating.
Hybrid fusion model. This model (Figure 2) adopts a hybrid approach of early and
late fusion. Written reflection embeddings and game trace logs are concatenated as in-
put (i.e., early fusion) to a GRU layer. The output is passed through dense and dropout
layers. The pre-test scores are combined with the output (i.e., late fusion) and passed
through dense layers for predicting post-test score and time-series reflection rating.
Fig. 2. Hybrid fusion model for multi-task learning.
5 Results
To evaluate each model, we use student-level 5-fold cross validation. For the training
set in each fold, we perform an 80-20 split to create a training and validation set, re-
spectively. For evaluating model performance, we use R2 score and MSE metrics. We
use a random forest (RF) model as a baseline. This model takes one subsequence as
input each time and predicts each label individually (i.e., single-task models only). We
obtain one final post-test score by averaging multiple subsequence-level predictions for
each student, since post-test score for a student is the same across all subsequences. On
the other hand, number of reflection ratings varies per student. We thus average predic-
tions across actions performed between consecutive reflection prompts.
The average cross-validation results comparing the performance of single and multi-
task models for different data fusion techniques can be seen in Table 1. For multimodal
MTL experiments, the hybrid and late fusion GRU models have similar performance
on post-test score prediction (R2 score 0.30 and MSE 0.026), while the hybrid fusion
GRU model outperforms both early and late fusion models for time-series reflection
7
rating prediction (R2 score 0.28 and MSE 0.004). For single-task models, we note that
the best performing GRU models show similar performance on post-test score predic-
tion as our RF baseline with R2 score 0.20 and MSE 0.030. However, all single-task
models perform poorly for reflection rating prediction, as they exhibit negative R2
scores. This indicates that single-task learning is not an effective modeling approach
for the task, fitting worse than the average value of unseen data. We further evaluate
the contribution of each modality in the performance of the best performing models
(i.e., GRUs with hybrid fusion) by testing different combinations of input modalities.
We compare single and multi-task models’ performance for post-test score prediction
in Table 2 and for time-series reflection rating prediction in Table 3. A model has better
performance if it has higher R2 score and lower MSE. The results show that best per-
formance is achieved with MTL models that utilize all three modalities.
Table 1. Comparison of predictive performance of stealth assessment models using different
data fusion techniques along with the random forest (RF) baseline (STL: single-task learning,
MTL: multi-task learning, EF: early fusion, LF: late fusion).
Models Post-test score Post-test score Time-series Time-series
prediction (R2) prediction (MSE) reflection rating reflection rating
prediction (R2) prediction (MSE)
STL-RF 0.20 0.030 -0.41 0.008
STL-EF 0.20 0.030 -0.32 0.008
STL-LF 0.19 0.031 -0.20 0.007
STL-Hybrid 0.20 0.030 -0.33 0.008
MTL-EF 0.15 0.032 0.08 0.005
MTL-LF 0.30 0.026 0.13 0.005
MTL-
0.30 0.026 0.28 0.004
Hybrid
Table 2. Comparisons of single and multi-task GRU models with hybrid fusion for predicting
post-test scores using different combinations of modalities.
Modalities Single-task Single-task Multi-task Multi-task
(R2) (MSE) (R2) (MSE)
Pre-test score 0.23 0.029 0.23 0.029
Reflection 0.08 0.035 0.11 0.033
Game trace -0.10 0.041 0.001 0.040
Pre-test, reflect 0.28 0.027 0.27 0.028
Pre-test, game trace 0.12 0.033 0.17 0.031
Reflect, game trace 0.09 0.034 0.15 0.032
Pre-test, reflect, game trace 0.20 0.030 0.30 0.026
8
We observe that the hybrid fusion, multi-task GRU model outperforms the RF base-
line by achieving an R2 score of 0.30 and 0.28 and MSE 0.026 and 0.004 for post-test
score and time-series reflection rating prediction, respectively. We also note that the
best single-task GRU models’ performance for post-test score prediction is achieved by
using a combination of pre-test scores and written reflections (Table 2).
Table 3. Comparisons of single-task and multi-task GRU models with hybrid fusion for pre-
dicting time-series reflection ratings using different combinations of modalities.
Modalities Single-task Single-task Multi-task Multi-task
(R2) (MSE) (R2) (MSE)
Pre-test score -0.29 0.008 -0.29 0.007
Reflect -0.24 0.007 0.04 0.005
Game trace -0.46 0.008 -0.22 0.007
Pre-test, reflect -0.27 0.008 0.11 0.005
Pre-test, game trace -0.23 0.007 -0.16 0.006
Reflect, game trace -0.18 0.007 0.17 0.004
Pre-test, reflect, game trace -0.33 0.008 0.28 0.004
The single-task learning results indicate that students’ post-test scores primarily de-
pend on prior knowledge about the subject matter and how well they reflect in the game,
while game trace data added noise to the model by decreasing predictive performance.
However, we observe that MTL (0.30 R2 score, 0.026 MSE and 0.28 R2 score, 0.004
MSE for post-test scores and time-series reflection ratings respectively) lends itself to
successfully model the features, outperforming all single-task models for both tasks.
Among the three fusion techniques, hybrid fusion outperforms both early and late fu-
sion in MTL, suggesting that (1) combining gameplay logs with written response em-
beddings early facilitates modeling of complementary relationships between these two
modalities, and (2) fusing intermediate representations learned from gameplay logs and
written response features with pre-test features late is effective for both prediction tasks.
Together with the significant improvement achieved by MTL over single-task learning
utilizing multimodal data for time-series reflection rating prediction, the results suggest
it is beneficial to simultaneously learn shared intermediate representations using labels
from two related tasks, boosting predictive accuracies of both learning outcomes.
6 Conclusion
Stealth assessment in game-based learning environments shows significant potential to
support effective learning experiences for students. Given the positive relationship be-
tween student reflection and learning, we introduced a multimodal, multi-task stealth
assessment framework to dynamically infer student competencies on content
knowledge and reflection. We investigated multimodal data fusion techniques for GRU
models to predict post-test scores and a series of written reflection ratings utilizing pre-
9
test scores, reflection embeddings, and game trace logs. We derived ELMo embeddings
to represent written responses and explored three multimodal data fusion mechanisms
including early, late and hybrid fusion combined with single and multi-task learning
architectures. The results suggest that the multi-task, hybrid fusion model significantly
outperforms the RF baseline. The best predictive performance was achieved by com-
bining all modalities in a multi-task setting using our hybrid fusion GRU model.
In future work it will be important to experiment with other contextual language
embeddings to further improve models’ generalization performance. Subsequences at
later timestamps are expected to be better predictors of post-test scores. Early prediction
measures for regression tasks could help us understand how early in the game we can
accurately predict scores. It will be important to investigate additional data modalities
to pick up cues that could further improve prediction of learning outcomes. Other
measures including affect and engagement have important relationships to learning and
could offer additional insight into learning processes and outcomes.
References
1. Clark, D. B., Tanner-Smith, E. E., Killingsworth, S. S.: Digital games, design, and learning:
A systematic review and meta-analysis. Review of Educational Research, 86(1), 79-122
(2016).
2. Qian, M., Clark, K. R.: Game-based learning and 21st century skills: A review of recent re-
search. Computers in Human Behavior, 63, 50-58 (2016).
3. Plass, J. L., Mayer, R. E., Homer, B. D. (Eds.).: Handbook of Game-Based Learning. MIT
Press (2020).
4. Carpenter, D., Emerson, A., Mott, B. W., Saleh, A., Glazewski, K. D., Hmelo-Silver, C. E.,
Lester, J. C.: Detecting Off-Task Behavior from Student Dialogue in Game-Based
Collaborative Learning. In: International Conference on Artificial Intelligence in Education,
pp. 55-66. Springer, Cham (2020).
5. Geden, M., Emerson, A., Carpenter, D., Rowe, J., Azevedo, R., Lester, J.: Predictive student
modeling in game-based learning environments with word embedding representations of
reflection. In: International Journal of Artificial Intelligence in Education, 31(1), 1-23
(2021).
6. Shute, V. J.: Stealth assessment in computer-based games to support learning. Computer
Games and Instruction, 55(2), 503-524 (2011).
7. Min, W., Frankosky, M. H., Mott, B. W., Rowe, J. P., Smith, A., Wiebe, E., Boyer, K. E.,
Lester, J. C.: DeepStealth: Game-based learning stealth assessment with deep neural
networks. IEEE Transactions on Learning Technologies, 13(2), pp. 312-325 (2019).
8. Mislevy, R. J., Almond, R. G., Lukas, J. F.: A brief introduction to evidence‐centered
design. ETS Research Report Series, 2003(1), i-29, (2003).
9. Jung, Y., Wise, A. F.: How and how well do students reflect? multi-dimensional automated
reflection assessment in health professions education. In: Proceedings of the Tenth
International Conference on Learning Analytics & Knowledge, pp. 595-604. (2020).
10. Peters, M. E.: Deep contextualized word representations. arXiv preprint arXiv:1802.05365
(2018).
11. Cho, K., Van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H.,
Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical
machine translation. arXiv preprint arXiv:1406.1078 (2014).
10
12. Baltrušaitis, T., Ahuja, C., Morency, L. P.: Multimodal machine learning: A survey and
taxonomy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(2), 423-443
(2018).
13. Blikstein, P., Worsley, M.: Multimodal learning analytics and education data mining: Using
computational technologies to measure complex learning tasks. Journal of Learning Analyt-
ics, 3(2), 220-238 (2016).
14. Oviatt, S., Grafsgaard, J., Chen, L., Ochoa, X.: Multimodal learning analytics: Assessing
learners' mental state during the process of learning. In: The Handbook of Multimodal-Mul-
tisensor Interfaces: Signal Processing, Architectures, and Detection of Emotion and Cogni-
tion-Volume 2, pp. 331-374 (2018).
15. Aslan, S., Alyuz, N., Tanriover, C., Mete, S. E., Okur, E., D'Mello, S. K., Arslan Esme, A.:
Investigating the impact of a real-time, multimodal student engagement analytics technology
in authentic classrooms. In: Proceedings of the 2019 CHI Conference on Human Factors in
Computing Systems, pp. 1-12 (2019).
16. Emerson, A., Henderson, N., Rowe, J., Min, W., Lee, S., Minogue, J., Lester, J.: Early
Prediction of Visitor Engagement in Science Museums with Multimodal Learning
Analytics. In: Proceedings of the 2020 International Conference on Multimodal Interaction,
pp. 107-116 (2020).
17. Emerson, A., Henderson, N., Rowe, J., Min, W., Lee, S., Minogue, J., Lester, J.:
Investigating Visitor Engagement in Interactive Science Museum Exhibits with Multimodal
Bayesian Hierarchical Models. In: International Conference on Artificial Intelligence in
Education, pp. 165-176. Springer, Cham (2020).
18. Zheng, Y.: Methodologies for cross-domain data fusion: An overview. IEEE transactions on
big data, 1(1), 16-34 (2015).
19. Fu, Y.: Sparse real estate ranking with online user reviews and offline moving behaviors.
In: 2014 IEEE International Conference on Data Mining, pp. 120-129. IEEE (2014).
20. Zheng, Y., Liu, Y., Yuan, J., Xie, X.: Urban computing with taxicabs. In: Proceedings of the
13th International Conference on Ubiquitous Computing, pp. 89-98. (2011).
21. Yuan, N. J., Zheng, Y., Xie, X., Wang, Y., Zheng, K., Xiong, H.: Discovering urban
functional zones using latent activity trajectories. IEEE Transactions on Knowledge and
Data Engineering, 27(3), 712-725 (2014).
22. Henderson, N.: Improving affect detection in game-based learning with multimodal data
fusion. In: International Conference on Artificial Intelligence in Education, pp. 228-239.
Springer, Cham, 2020.
23. Kim, Y. J., Almond, R. G., Shute, V. J.: Applying evidence-centered design for the
development of game-based assessments in physics playground. International Journal of
Testing, 16(2), 142-163 (2016).
24. Luo, W., Litman, D.: Determining the quality of a student reflective response. In: The
Twenty-Ninth International FLAIRS Conference, pp. 226-231. (2016).
25. Carpenter, D., Geden, M., Rowe, J., Azevedo, R., Lester, J.: Automated Analysis of Middle
School Students’ Written Reflections During Game-Based Learning. In: International
Conference on Artificial Intelligence in Education, pp. 67-78. Springer, Cham (2020).
26. Zhang, Y., Yang, Q.: A survey on multi-task learning. IEEE Transactions on Knowledge
and Data Engineering. IEEE. (2021).
27. Rowe, J. P., Shores, L. R., Mott, B. W., Lester, J. C.: Integrating learning, problem solving,
and engagement in narrative-centered learning environments. International Journal of
Artificial Intelligence in Education, 21(1-2), 115-133 (2011).
28. Kingma, D. P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint
arXiv:1412.6980 (2014).