Process Mining in Learning Analytics: Benefits and Challenges

This research proposal aims to explore and evaluate the impact of process mining on learning analytics and investigate its benefits and challenges. The proposal discusses the role of process mining in digital transformation and its techniques in process management. It also explains the concept of learning analytics and its steps to optimize the learning process and environment. The proposal includes a literature review on process mining and learning analytics, highlighting the importance of these techniques in improving performance and learning quality. The methodology section outlines the problem statement, research questions, and experimental method to evaluate the impact of process mining on learning analytics. The proposal concludes with references to relevant studies on process mining and learning analytics.

Running head: RESEARCH PROPOSAL
Research proposal on "Process Mining in Learning Analytics: Benefits and challenges"
Name of the Student:
Name of the University:
Author note:

1RESEARCH PROPOSAL
Introduction
This research proposal aims to explore and evaluate the impact of process mining on the
learning analytics and investigate its benefits and challenges in the learning analytics. Process
mining has a crucial role in the digital transformation and it is a set of techniques in process
management. Process mining refers to the analysis methods of processes in the systems of a
business based on the data extracted from the event logs in the present information system of an
organization [1]. This system goes beyond the key data of the system or process and it
recognizes the contextual relationships of the business processes collected from the event logs,
which are presented in the form of graphics for diagnosing problems in the business system and
formulating improvement measures. Hence, process mining helps in detecting or diagnosing
problems in the business processes on the basis of the facts and not on the basis of intuition [2].
On the other hand, learning analytics refers to the measurement, collection, analysis and
reporting of the data regarding the learners and the learning contexts in order to understand and
optimize the learning process and the environment. Thus, learning analytics is based on the
above mentioned steps and it includes measures to observe the learners and process of learning,
reflect and improve the process and environment of learning and teaching [3]. Thus, it can be
said that the techniques of process mining include steps that are implemented to improve the
systems based on the knowledge gathered from the event logs and the system of learning
analytics includes steps to improve the learning process and organization on the basis of the data
measured, collected, analyzed and reported. Hence, there can be a potential positive outcome if
process mining can be implemented in learning analytics. Through this research study, the
benefits and challenges of incorporating process mining in the learning analytics will be
investigated and evaluated.

2RESEARCH PROPOSAL
Literature review
"A general process mining framework for correlating, predicting and clustering dynamic
behavior based on event logs." By Massimiliano De Leoni, Wil MP van der Aalst, and
Marcus Dees.
The above article describes the framework of a general process mining for the purpose of
correlation, prediction and clustering the dynamic business behavior on the basis of event logs.
The authors stated that process mining acts as a missing link between the data oriented analysis
techniques and model based process analysis. The organization put much effort on process
discovery, to replay the techniques for checking conformance and for analyzing the bottlenecks
in the systems. The organizations can address the compliances and performance issues by using
these techniques in a much easier manner. By applying the process mining framework, the
organizations can address various processes in a more systematic manner. The authors suggested
that process and data mining techniques should be implemented alongside to have a better
knowledge of the system performances and the defects by correlating the information gathered
from the processes and it helps in addressing those issues in a more precise and faster manner
[4].
"e‐Research and learning theory: What do sequence and process mining methods
contribute?." By Peter Reimann, Lina Markauskaite, and Maria Bannert.
In the above article written by Reimann, Markauskaite, and Bannert (2014), sequence and
process mining methods are highly useful in the leaning theories and e-research as these are

3RESEARCH PROPOSAL
highly data-intensive and helps in the development of the learning theories. The current data-
driven analytical techniques, such as the educational data mining and in its branch process
mining, are quite advanced and these techniques are grounded in the event focused and give and
ontologically flat idea of the learning phenomena. However, these techniques give a description
of the regularities of the events but these are unable to generate theoretical explanations of the
events. Thus, the authors suggested that the educational e-research systems must adopt more
nuanced or precise techniques to examine and theorizing the learning phenomena which can
provide information of the mechanisms applied as well as the contexts, in which the mechanisms
applied and realized. Thus, according to the authors, the methodological extensions of the e-
research and learning theories and the application of the process mining techniques should
include the three key aspects, that is, (1) stratified ontological frameworks, (2) multimodal data
collection and (3) dynamic analytical methods [5].
"Educational Data Mining and Learning Analytics: differences, similarities, and time
evolution." By Laura Calvet Liñán, and Ángel Alejandro Juan Pérez.
In the above article, the authors made a comparative study on the similarities, differences,
and time evolution between educational data mining and the learning analytics. The authors
highlighted that as technology is getting advanced rapidly, the learning process and techniques
are also getting changed. Online or e-learning has become a trend in the modern world and in
this learning techniques, a large amount of data is involved and extracting of valuable data
among all types of data or information is beneficial for improving the performance of the
students. The techniques of educational data mining and learning analytics are two new learning
techniques that involve the process of collection, analysis and interpretation of the educational
data available online. Hence, it can be inferred that the techniques for data mining is useful for

4RESEARCH PROPOSAL
not only accessing the large amount of data, but also for assessing the processes that can help to
improve the education techniques and learning quality [6].
"Data mining and analytics in the process industry: The role of machine learning." By
Zhiqiang Ge, Zhihuan Song, Steven X. Ding, and Biao Huang
The above article explored the role of machine learning in the data mining and analytics
in the process industry. The authors stated that data mining and analytics are important for
knowledge discovery and decision making based on the data. Machine learning is a process that
makes the knowledge extraction and detecting the defects easier by automating the systems.
Hence, it can be said that as more and more data are becoming accessible with the help of
advanced technology, machine learning and process mining are gaining more importance in
improving the performance of the systems [7].
From the above review of the literature, it can be said that while the importance of
process mining and other knowledge extraction techniques are increasing in a world with
advanced technology, learning analytics technique is also gaining importance in improving the
learning process. Not only for the businesses, but also in the education sector, the automated
systems are now being used to improve the performance and make the systems much faster.
However, it is also noticed that different authors focused on different approaches of process
mining and learning analytics as the systems are different and more precise research is required
to select the appropriate technique of process mining to get the optimum efficiency of the
learning analytics.

5RESEARCH PROPOSAL
Methodology
Problem statement: Learning analytics aims to improve the learning quality and environment
through collection and analysis of data and process mining is a technique for collecting data from
events log and analyzing those to make the system faster and more error free. Thus, the problem
statement for this study is to analyze the impact of process mining on the learning analytics to
improve the process of learning.
Research questions:
1. How the process mining can be implemented in the learning analytics techniques?
2. What are the benefits and challenges of implementing the process mining in improving
the performance of learning analytics?
The research questions can be answered by applying experimental method. Two groups of
participants will be chosen and one group would be asked to apply process mining techniques on
their learning analytics process and the other would not apply the process mining technique. The
participants will be chosen from University of Sydney, studying in the IT department, who
would be well aware of the process mining techniques.
The experiment would be conducted for 1 month and after that, feedback would be
collected from both the groups. Further, they will be asked to give an evaluation test on their
learning analytics to find out the impact of process mining and if the group using process mining
performs better, then it can be inferred that process mining is beneficial for learning analytics.
The feedback from the groups will help in gaining knowledge about the benefits and challenges
of the process mining application on their learning analytics, while the evaluation test on the
performance will give the solution that if process mining actually helped in learning analytics.

6RESEARCH PROPOSAL
Thus, through a deductive and exploratory research, the implementation of process
mining technique on the learning analytics will be evaluated and both qualitative and quantitative
data will be collected from the two groups of participants and mixed method, that is, both
qualitative and quantitative analysis method will be applied to get the findings. Descriptive
method will be used to analyze the qualitative feedback by the students, and mean comparison of
the test scores will be done using quantitative methods to get the findings. Thus, by following the
above method the impact of the process mining techniques on the learning analytics will be
evaluated and its benefits and challenges will be explored.

7RESEARCH PROPOSAL
References
[1] Van Der Aalst, Wil. Process mining: discovery, conformance and enhancement of business
processes. Vol. 2. Heidelberg: Springer, 2011.
[2] Bogarín, Alejandro, Rebeca Cerezo, and Cristóbal Romero. "A survey on educational process
mining." Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 8, no. 1
(2018): e1230.
[3] Schumacher, Clara, and Dirk Ifenthaler. "Features students really expect from learning
analytics." Computers in Human Behavior 78 (2018): 397-407.
[4] De Leoni, Massimiliano, Wil MP van der Aalst, and Marcus Dees. "A general process mining
framework for correlating, predicting and clustering dynamic behavior based on event
logs." Information Systems 56 (2016): 235-257.
[5] Reimann, Peter, Lina Markauskaite, and Maria Bannert. "e‐Research and learning theory:
What do sequence and process mining methods contribute?." British Journal of Educational
Technology 45, no. 3 (2014): 528-540.
[6] Liñán, Laura Calvet, and Ángel Alejandro Juan Pérez. "Educational Data Mining and
Learning Analytics: differences, similarities, and time evolution." International Journal of
Educational Technology in Higher Education 12, no. 3 (2015): 98-112.
[7] Ge, Zhiqiang, Zhihuan Song, Steven X. Ding, and Biao Huang. "Data mining and analytics in
the process industry: The role of machine learning." IEEE Access 5 (2017): 20590-20616.

8RESEARCH PROPOSAL