ChapterPDF Available

Developments in Data Science and Artificial Intelligence in Learning Technology and CCI Research


Abstract and Figures

This book is focusing on experimental studies in learning technology and CCI research. During the last years, the areas of data science and AI have influenced different aspects of human-factors IT-related research in general and learning technology and CCI research in particular. Therefore, although this book does not provide a deep discussion on how data science and AI have influenced contemporary learning technology and CCI research; in this chapter, we provide a brief presentation of the developments in data science and AI, and the role of those developments in learning technology and CCI research.
Content may be subject to copyright.
Chapter 9
Developments inData Science
andArticial Intelligencein Learning
Technology andCCI Research
Abstract This book is focusing on experimental studies in learning technology and
CCI research. During the last years, the areas of data science and AI have inuenced
different aspects of human-factors IT-related research in general and learning tech-
nology and CCI research in particular. Therefore, although this book does not pro-
vide a deep discussion on how data science and AI have inuenced contemporary
learning technology and CCI research; in this chapter, we provide a brief presenta-
tion of the developments in data science and AI, and the role of those developments
in learning technology and CCI research.
Keywords Data science · Articial intelligence · Learning technology ·
Multimodal data
9.1 Data Science
Most CCI and learning technology studies are conducted on small groups of partici-
pants, often from a homogeneous context (e.g., the same school or a similar back-
ground). With the emergence of online education and learning-at-scale technologies
(e.g., MOOCs, LMSs, ITSs, open courseware, and community tutorial systems such
as Stack Overow), millions of participants in different parts of the world and from
different backgrounds can engage with CCI and learning technology systems. New
forms of data require new methodologies. As we have described in this book, a clas-
sical approach in a CCI and learning technology study would involve some dozens
of end-users participating in each condition and would apply hypothesis-testing
analysis (e.g., t-tests or ANOVAs). Since the datasets (and the respective data points)
would be small, only large effects would be detectable, and so signicance would
imply relevance. On the other hand, if the number of students is large, we could
easily end up rejecting the null hypothesis and detecting an effect that is irrelevant
in practice (Kidzinski etal., 2016).
As mentioned above, in CCI and learning technology research, typical data anal-
ysis techniques (e.g., analysis of variance, correlations, and regressions) are usually
© The Authors 2022
M. Giannakos, Experimental Studies in Learning Technology and Child–
Computer Interaction, SpringerBriefs in Educational Communications and
employed to explore the RQs and test the hypotheses, where the formulation of the
RQs and the hypothesis formation are guided by previous work and/or theories.
However, when dealing with massive amounts of data (e.g., from MOOCs or LMSs)
or rich multimodal data (e.g., video, eye-tracking, or other sensor data), different
statistical analysis techniques need to be employed (including predictions and clas-
sications). Given that learning/educational scientists and designers are often unfa-
miliar with contemporary modeling techniques, this has prompted an increasing
number of computer scientists, statisticians, and data scientists to engage with CCI
and learning technology research. In many cases, because of the nature of the prob-
lem and the data (e.g., online learning), contextual knowledge (e.g., how someone
is using YouTube or Stack Overow in their learning) is either not relevant or cannot
be captured (e.g., in a MOOC). In such cases, we see research initiatives in CCI and
learning technology that seek to address problems in the absence of contextual
This type of decontextualized and large-scale experimentation in CCI and learn-
ing technology research lies outside the scope of this book. However, we would like
to emphasize that exploratory data analysis techniques (Tukey, 1977) can be useful,
particularly for nding an adequate data transformation and for outlier detections.
Explorations of this type can bring new insights and hypotheses and eventually
close the cycle (see Fig.9.1). For those interested in how to employ advanced data
science and machine learning (ML) techniques in the context of learning, we pro-
vide elsewhere a mini-tutorial on methodologies for forming and testing hypotheses
in large educational datasets (Kidzinski etal., 2016). We also present practical guid-
ance for building data-driven predictive models with state-of-the-art ML methods,
using the R and CARET packages because of their simplicity and the ease of access
to the most recent ML methods.
Fig. 9.1 Data-driven CCI and learning technology in at-scale contexts. (Adapted from Kidzinski
etal., 2016)
9 Developments in Data Science and Articial Intelligence in Learning Technology
9.2 Articial Intelligence
Articial intelligence (AI) in CCI and learning technology research is traditionally
represented by AI in education (AIED), intelligent user interfaces (IUI), and the ITS
communities, and involves a wide spectrum of technologies and approaches. In
recent years, we have seen AI technologies and approaches employed in almost
every CCI and learning technology community. Since the 1980s, researchers have
been interested in the association between learning and AI, although initially this
mainly meant a focus on knowledge representation, reasoning, and learning (Self,
2015, p. 5). Russell and Norvig (2021) have described AI as a technology that
includes problem solving, representation, reasoning on the basis of certain/uncer-
tain knowledge, ML, and communicating, perceiving, and acting techniques for
designing and developing intelligent agents. More recently, we have seen various
developments in sensing technologies, analytics, and visualization, as well as cogni-
tive technologies and architectures that have boosted the use of AI to support teach-
ing and learning. The International Journal of Articial Intelligence in Education
(IJAIED1) describes the focus of the AIED eld as the development and design of
AI-powered computer-based learning systems, including agent-based learning envi-
ronments, Bayesian and other statistical methods, cognitive tools for learning, intel-
ligent agents on the Internet, natural language interfaces for instructional systems,
and real-world applications of AIED systems.
The topic of AI and advanced data science techniques in education is not central
to this book; nevertheless given recent advances in data science, this book would not
be complete if we did not introduce the reader to these advancements. Drawing
from a recent literature review on AIED (Chen etal., 2020), we see that contempo-
rary AI learning systems incorporate various techniques and technologies, such as
recommendations, knowledge understanding and ML, data mining, and knowledge
models (Avella et al., 2016). There are three main components of an AI-powered
learning system: the educational data collections from learners’ and teachers’ activ-
ities, the techniques or modeling employed (e.g., knowledge inference or ML), and
the system’s intelligence as expressed through different intelligent technologies
(Kim etal., 2018). Figure9.2 shows how these three components work together to
enable AI functionalities in the learning system.
As Fig.9.2 makes clear, the quality of data collection is of paramount importance
if an AI learning system is to operate efciently. In the context of CCI, we see chil-
dren’s toys evolving through advances in embedded electronics, digital capabilities,
and wireless connectivity that combine different capabilities such as networking,
processing, and intelligent reasoning. As we see from a recent IJCCI special issue
in AI and CCI,2 the increasing use of such interactive objects in CCI and the rise of
1 International Journal of Articial Intelligence in Education:
9.2 Articial Intelligence
Fig. 9.2 Representation of AI-powered educational systems, which consists of the data collec-
tions layer (e.g., educational and interaction data), the modeling techniques which developing
different intelligence based on the data collections, and the system’s intelligence part that provides
the technologies needs to provide the intelligence as a service to the user
AI techniques through data-driven methods reinforce intelligent features and adap-
tivity, but they also bring many signicant privacy issues and ethical concerns.
In summary, AI technologies can amplify different areas of human abilities,
including physical, memory, perception, cognition and learning (Shneiderman,
2020). Examples of technologies that leverage AI to amplify human abilities are,
information representation/ awareness/ reection technologies (e.g., dashboards),
in-situ human-computer interaction technologies (e.g., augmented reality and ubiq-
uitous displays), and technologies with implicit and adaptive control (e.g., gaze
tracking). On the contrary of autonomous AI systems that focus on replacing human
decision making, those AI technologies employ the notion of “intelligence augmen-
tation” (IA) that attempts to support human abilities (e.g., decision making, cogni-
tion) rather than replacing them. Contemporary learning systems employ different
information representation and IA techniques via powerful interfaces and commu-
nication modalities (e.g., dashboards, adaptive navigation). Those interfaces and
communication modalities combine various log data and provide explicit, easy-to-
understand, and concise ways of presenting valuable information to support human
9.3 Sensor Data andMultimodal Learning Analytics
The use of sensors to support research on human-factors IT-related elds (especially
in the context of learning) is not new. To some extent, the use of sensors (e.g., via
cameras) has been central to LS research for several decades, as the popularity of
qualitative video analysis indicates. However, in recent years, a proliferation of
wearable and remote devices has made sensing widely available and affordable in
the context of education, and a growing number of related studies have been pub-
lished (Sharma & Giannakos, 2020). In addition, new methods, models, and algo-
rithms have been developed (Blikstein & Worsley, 2016) that enable the continuous,
unobtrusive, automated, and useful application of sensors during learning. Thanks
to these devices and techniques, it is possible to monitor indices that are argued to
9 Developments in Data Science and Articial Intelligence in Learning Technology
be signicant for learning but have often been ignored because of the difculties of
measuring and interpreting them dynamically (Giannakos etal., 2020). Despite the
challenges of using sensor data, previous studies have advocated the use of sensor
technologies to capture complex interactions exchanged between learners/children
and the interactive systems they engage with (Giannakos etal., 2022). Work on
quantied-self movement has shown potential in using sensor data to support human
decision making (e.g., in relation to diet, tness, and lifestyle), self-monitoring,
self-awareness, and self-reection (Qi etal., 2018), as well as potential in learning
technology (Giannakos etal., 2020) and CCI research (Lee-Cultura etal., 2020).
Research on collecting, pre-processing (e.g., data “cleaning”), synchronizing,
and analyzing sensor data streams can be found in neighboring elds such as HCI
and ubiquitous computing, with applications dating from the 1980s onward (Weiser
etal., 1999). Sensor data has also been at the center of several learning technology
and HCI communities, such as ITS (D’Mello etal., 2010), educational data mining
(EDM) (Romero etal., 2010), and user modeling, adaptation, and personalization
(UMAP) (Desmarais & Baker, 2012). The typical steps when using sensors include
data collection, pre-processing, engineering, mining/analysis, validation, contextu-
alization, and making sense of the results. These steps are somewhat different
depending on whether there is a data-driven or a theory/hypothesis-driven approach,
on the research design employed (e.g., qualitative or quantitative), and on the epis-
temic stance of the researchers (e.g., positivist or post-positivist) (Giannakos etal.,
2022). In the last decade, there has been much discussion around the use of sensors
in learning technology and CCI (Giannakos etal., 2022; Markopoulos etal., 2021),
with different communities using different nomenclature to describe various facets
of sensor data (e.g., sensor data in education, sensing, physiological analytics, ubiq-
uitous data in education, and multimodal learning analytics).
In a recent chapter focusing on the use of sensor data in education (Giannakos
etal., 2022), the authors described the advantages and qualities of sensor data in
terms of three pillars. First and foremost, whereas computer logs enable us to cap-
ture learners’ actions in binary fashion, sensors go further in terms of richness,
allowing us to capture information about learners regardless of whether they have
completed an action (e.g., while watching a video but not interacting with it, or
interacting with a nondigital object). Second, sensors provide temporality by being
sensitive to temporal changes and giving us direct access to indices that are relevant
to cognitive and affective processes. Third, instead of reductive representation of the
user and learner experience, sensor data provide granularity, allowing us to capture
very low-level insights and focus our analysis on different aspects. Those qualities
of sensor data, combined with advances in data science and AI, can provide power-
ful learning capabilities. For instance, they can provide access to indices relevant to
cognitive and affective processes (see Fig.9.3, left), or they can incorporate sensor
data into a learning system’s functionality (e.g., embodiment) or intelligence (e.g.,
affective support) via appropriate technological architectures (see Fig.9.3, right).
To summarize this chapter, sensor data have several qualities that support inter-
action with the technology. Many of those qualities are benecial for learning sys-
tems and can help us to improve the effectiveness of those systems. At the same
9.3 Sensor Data andMultimodal Learning Analytics
Fig. 9.3 Meaningful sensor data from a child interacting with a learning technology. (From
Giannakos etal., 2021; with permission by IEEE). Left: The vertical lines show the child’s response
correctness (green for correct, red for incorrect), the solid red curves show the child’s indices, and
the dashed-green curves show the average for the whole class. Right: The logic of a system that
leverages sensor data
time, sensor data introduce challenges that need to be tackled to allow contempo-
rary learning technology research and practice to realize the potential benets.
Contemporary research on sensor data and advanced computational analyses has
introduced the term “multimodal learning analytics” (MMLA) and led to the forma-
tion of the a special interest group in the context of the Society for Learning
Analytics Research (SoLAR).3
Avella, J. T., Kebritchi, M., Nunn, S.G., & Kanai, T. (2016). Learning analytics methods, ben-
ets, and challenges in higher education: A systematic literature review. Online Learning,
20(2), 13–29.
Blikstein, P., & Worsley, M. (2016). Multimodal learning analytics and education data mining:
Using computational technologies to measure complex learning tasks. Journal of Learning
Analytics, 3(2), 220–238.
Chen, L., Chen, P., & Lin, Z. (2020). Articial intelligence in education: A review. IEEE Access,
8, 75264–75278.
D’Mello, S., Lehman, B., Sullins, J., Daigle, R., Combs, R., Vogt, K., Perkins, L., & Graesser,
A. (2010). A time for emoting: When affect-sensitivity is and isn’t effective at promoting deep
learning. In International conference on intelligent tutoring systems (pp.245–254).
Desmarais, M.C., & Baker, R.S. (2012). A review of recent advances in learner and skill modeling
in intelligent learning environments. User Modeling and User-AdaptedInteraction, 22(1), 9–38.
Giannakos, M.N., Sharma, K., Papavlasopoulou, S., Pappas, I.O., & Kostakos, V. (2020). Fitbit
for learning: Towards capturing the learning experience using wearable sensing. International
Journal of Human-Computer Studies, 136, 102384.
9 Developments in Data Science and Articial Intelligence in Learning Technology
Giannakos, M. N., Lee-Cultura, S., & Sharma, K. (2021). Sensing-based analytics in educa-
tion: The rise of multimodal data enabled learning systems. IT Professional. doi: 10.1109/
Giannakos, M., Cukurova, M., & Papavlasopoulou, S. (2022). Sensor-based analytics in education:
Lessons learned from research in multimodal learning analytics. In M.Giannakos, D.Spikol,
D.DiMitri, K.Sharma, X. Ochoa & R.Hammad (Eds.). The Multimodal Learning Analytics
Handbook. Springer.
Kidziński, Ł., Giannakos, M., Sampson, D.G., & Dillenbourg, P. (2016). A tutorial on machine
learning in educational science. In State-of-the-art and future directions of smart learning
(pp.453–459). Springer.
Kim, Y., Soyata, T., & Behnagh, R. F. (2018). Towards emotionally aware AI smart classroom:
Current issues and directions for engineering and education. IEEE Access, 6, 5308–5331.
Lee-Cultura, S., Sharma, K., Papavlasopoulou, S., Retalis, S., & Giannakos, M. (2020). Using
sensing technologies to explain children’s self-representation in motion-based educational
games. In Proceedings of the interaction design and children conference (pp. 541–555).
Markopoulos, P., Read, J., & Giannakos, M. (2021). Design of digital technologies for children.
In G. Salvendy & W. Karwowski (Eds.), Handbook of human factors and ergonomics (5th
ed.). Wiley.
Qi, J., Yang, P., Waraich, A., Deng, Z., Zhao, Y., & Yang, Y. (2018). Examining sensor-based physi-
cal activity recognition and monitoring for healthcare using internet of things: A systematic
review. Journal of Biomedical Informatics, 87, 138–153.
Romero, C., Ventura, S., Pechenizkiy, M., & Baker, R.S. (2010). Handbook of educational data
mining. CRC Press.
Russell, S., & Norvig, P. (2021). Articial intelligence: A modern approach, global (Vol. 19, 4th
ed., p.23). Pearson.
Self, J. (2015). The birth of IJAIED. International Journal of Articial Intelligence in Education,
26(1), 4–12.
Sharma, K., & Giannakos, M. (2020). Multimodal data capabilities for learning: What can
multimodal data tell us about learning? British Journal of Educational Technology, 51(5),
Shneiderman, B. (2020). Human-centered articial intelligence: Reliable, safe & trustworthy.
International Journal of Human–Computer Interaction, 36(6), 495–504.
Tukey, J.W. (1977). Exploratory data analysis (Vol. 2, pp.131–160).
Weiser, M., Gold, R., & Brown, J.S. (1999). The origins of ubiquitous computing research at parc
in the late 1980s. IBM Systems Journal, 38(4), 693–696.
Open Access This chapter is licensed under the terms of the Creative Commons Attribution 4.0
International License (, which permits use, sharing,
adaptation, distribution and reproduction in any medium or format, as long as you give appropriate
credit to the original author(s) and the source, provide a link to the Creative Commons license and
indicate if changes were made.
The images or other third party material in this chapter are included in the chapter’s Creative
Commons license, unless indicated otherwise in a credit line to the material. If material is not
included in the chapter’s Creative Commons license and your intended use is not permitted by
statutory regulation or exceeds the permitted use, you will need to obtain permission directly from
the copyright holder.
ResearchGate has not been able to resolve any citations for this publication.
Full-text available
The growth and uptake of educational technology has significantly reshaped the delivery of distance and online learning. With an unprecedented number of learners engaging with online modes of education, there is a growing need to understand the underlying student enrolment motivations, goals and learning behaviours evolving from a highly diverse student population. Research in learning analytics has advanced the use of digital data to understand student learning processes. However, there remains a limited understanding of how non-traditional learner characteristics, needs and motivational factors influence their learning behaviour and engagement strategies. Survey data from 232 students enrolled in fully online degree programs at a large public research university in Australia has been examined and used to represent 1687 students that have not completed the survey. To characterise the larger population of students, we combined their demographics, digital trace data, and course performance to provide richer insights of non-traditional learners in online learning. Data science approaches are applied, including an unsupervised machine learning technique that revealed the results of six unique learner profiles, clearly differentiated by their motivation, demographic, engagement and performance. While the findings show that each learner profile faces unique study challenges, there are also unique opportunities associated with each profile that could be utilised to improve their learning outcomes. The practical implications of the study on teaching practices are further discussed.
Full-text available
The proliferation of sensing technology and the produced sensing-based analytics (SBA) has driven several fields in the development of tools and methods that have transformed their industries. The utilization of SBA fulfills the vision of integrating many sources of information, coming from different modalities (e.g., affective, cognitive, and embodiment), to strengthen learning systems’ capacity (e.g., adaptation, promote awareness, and reflection). The authors present a practical framework that outlines four phases that can enable learning systems to leverage on multimodal data coming from SBA. Moreover, the authors showcase the benefits of SBA through a case study and discuss how sensing integration can advance contemporary learning systems.
Full-text available
Background Problem-solving is a multidimensional and dynamic process that requires and interlinks cognitive, metacognitive, and affective dimensions of learning. However, current approaches practiced in computing education research (CER) are not sufficient to capture information beyond the basic programming process data (i.e., IDE-log data). Therefore, how cognition and affect intertwine and unfold over time in programming problem-solving activities are rarely investigated. Objectives In this study, we examined how the theory-informed measures from multimodal data that we have selected as proxies for cognitive and affective dimensions of learning, are associated with student performance, and in comparison, to prior-knowledge. Methods A high-frequency temporal data was collected with a camera, an electroencephalogram, and an eye-tracker from 40 computer science students (bachelor and master studies) in the context of a code-debugging activity. To study the cognitive processes associated with learning we focused on cognitive load theory (CLT) and the human information processing model. In addition, we complemented CLT with the model of affective dynamics in learning to avoid the machine reductionism perspective. Results Our findings demonstrated that attention, convergent thinking, and frustration were positively correlated with students' successful code-debugging (i.e., performance), and frequently manifested by high performing participants. Cognitive load, memory load, and boredom were negatively correlated with students' performance, and typically manifested by low performing participants. Implications Extending the context of analysis in reference to student cognitive processes and affective states, affords educators not just to identify lower performers, but also to understand the potential reasons behind their performance, making our method an important contribution in the confluence of CER and the learning technology communities. In addition, the insights extracted from our analyses allow us to discuss potential avenues for improving learning design and the design of interactive learning systems to support the development of students' problem-solving skills. Lay Description What is currently known about the subject matter ● Problem-solving interlinks cognitive, affective and metacognitive dimensions of learning. ● In digital settings instructors struggle to distinguish cognitive-affective states of students. ● Learning technologies require interventions based on cognitive-affective states of students. What the paper adds ● When and what cognitive-affective states are triggered during solving a programming problem. ● What and how measures as proxies for cognitive-affective states are associated with performance. ● Emphasizes the benefits of augmenting IDE-log data with sensor data in the context of learning design. Implications of study findings for practitioners ● Methodology guidelines to identify and model variability in humans' natural behaviours. ● Importance of content and instructions personalization for student engagement and learning. ● Identification of multimodal data proxies for flexible and adaptive multimodal interfaces.
Full-text available
Although there is an increased focus on the ethical responsibilities of designers when designing children’s technologies, there are few academic examples on what it entails to teach this to design students. We have therefore set out to explore the most common ethical dilemmas experienced by design students in child-computer interaction (CCI) when interacting with children in the field. This case study article reports on an analysis of the situated ethical experiences from 45 international master students in interaction design during their projects to design children’s technologies. The main research question for this paper is what common ethical dilemmas students in CCI experience when involving children in their design process. The dilemmas we present stem from the written home exams of the students in our course and have been clustered under three temporally relevant themes: Selection of participants, Informed Consent, and Working with children. These situational ethical dilemmas can be used by teachers in the field to complement the formal ethical guidelines provided to students and have a discussion on how to deal with them in their own practice.
Full-text available
Researchers and practitioners in learning sciences, educational technology and child-computer interaction often argue that fun is an essential element of learning. Therefore, researchers in the above fields aim to explore how learning activities could be made more enjoyable in order to facilitate engagement in the learning process and to improve the learning outcomes. Despite such wide interest, there has been little systematic effort to define and measure fun. The herein introduced research aims to (a) define the term “fun” and (b) to create a tool for the reliable measurement of it. In the first study testing the initial item pool 75 students ( μ age = 11.78); in the think-aloud study testing the comprehensibility of the items six 11-year-old children and in the final validation study, 128 students ( μ age = 12.15) participated. We applied a deductive scale development approach. For the model testing, CFA was used and second-order latent variable models were fitted. In this paper, we conceptualize the term of fun and introduce the final 18-item version of the FunQ that consists of six dimensions ( Autonomy , Challenge , Delight , Immersion , Loss of Social Barriers and Stress ) and bears with the appropriate validity and reliability measures ( ω overall = 0.875 and ω partial = 0.864; RMSEA = 0.052 and SRMR = 0.072). We contribute with (a) a review of the literature regarding the concept of fun, (b) a conception of fun as a multidimensional theoretically motivated concept, (c) a multidimensional instrument for assessing experienced fun—the FunQ—and (d) a psychometric evaluation of the proposed instrument. FunQ is put forward as a reliable and much-needed addition to the current palette of instruments.
The use of sensors to support learning research and practice is not new, whether in the context of wearable technology, context-aware technology, ubiquitous systems or else. Nevertheless, the proliferation of sensing technology has driven the field of learning technology in the development of tools and methods that can generate and leverage sensor-based analytics (SBA) to support complex learning processes. SBA fulfills the vision of integrating multiple sources of information, coming from different channels to strengthen learning systems' desired features (e.g., adaptation, affect detection) and augment learners' abilities (e.g., through embodied interaction and cognition). In addition, it offers a promising avenue for improving the research measurements in the field. In this chapter, the authors present how SBA has advanced learning technology through the lenses of their offered qualities, indented objectives and inevitable challenges. Through three case study examples, we showcase how those advancements are reflected in contemporary Multimodal Learning Analytics (MMLA) research. The chapter is concluded with a discussion on the role of SBA and a future research agenda that depicts how the lessons learned from the encountered challenges of MMLA can help us further improve the adoption of SBA for learning technology research and practice.
This chapter provides an introduction and an overview of this edited book on Multimodal Learning Analytics (MMLA). The goal of this book is to introduce the reader to the field of MMLA and provide a comprehensive overview of contemporary MMLA research. The contributions come from diverse contexts to support different objectives and stakeholders (e.g., learning scientists, policymakers, technologists). In this first introductory chapter, we present the history of MMLA and the various ongoing challenges, giving a brief overview of the contributions of the book, and conclude by highlighting the potential emerging technologies and practices connected with MMLA.
This chapter focuses on children aged around 5-11 insofar as this is the population most able to extract value from digital content while also being intrinsically different from older children in terms of their design needs. The need for technology designers to understand their intended users is well established in the fields of human-computer interaction and ergonomics. Language and reading abilities, and the ability to abstract and keep focused attention, vary substantially between different ages, meaning the use of text in interactive applications needs careful consideration. Child–Computer Interaction is the area of scientific investigation that concerns the phenomena surrounding the interaction between children and computational and communication technologies. User interface designers need to take into account children's diverse and developing abilities to perceive information presented on the interface and to operate input devices. Children may lack the cognitive and social skills required to carry out the evaluation procedures.
With the wide expansion of distributed learning environments the way we learn became more diverse than ever. This poses an opportunity to incorporate different data sources of learning traces that can offer broader insights into learner behavior and the intricacies of the learning process. We argue that combining analytics across different e-learning systems can measure the effectiveness of learning designs and maximize learning opportunities in distributed learning settings. As a step towards this goal, in this study, we considered how to broaden the context of a single learning environment into a learning ecosystem that integrates three separate e-learning systems. We present a cross-platform architecture that captures, integrates, and stores learning-related data from the learning ecosystem. To prove the feasibility and the benefit of the cross-platform architecture, we used regression and classification techniques to generate interpretable models with analytics that are relevant for instructors and learners in understanding learning behavior and making sense of the instructional method on learning performance. The results show that combining data across multiple e-learning systems improves the classification accuracy compared to data from a single learning system by a factor of 5. Our work highlights the value of cross-platform analytics and presents a springboard for the creation of new cross-systems data-driven research practices.