Content uploaded by Silvia Gaftandzhieva
Author content
All content in this area was uploaded by Silvia Gaftandzhieva on Apr 26, 2019
Content may be subject to copyright.
LEARNING ANALYTICS FROM THE TEACHER’S PERSPECTIVE: A
MOBILE APP
S. Gaftandzhieva, R. Doneva, G. Pashev
University of Plovdiv "Paisii Hilendarski" (BULGARIA)
Abstract
The wide range of data produced by participants in the learning processes led to increased interest in
the collection and analysis of data to support data-driven decision making at all levels of educational
institutions. The paper is devoted to the emerging field of Learning Analytics from the teacher’s
perspective. It proposes a set of indicators that Learning Analytics should provide to help teachers be
more reflective in their teaching practice, to improve the quality of education provided in their courses
and relevance of the learning materials, to discover more about students’ learning, to track and predict
students’ performance, to identify potential issues and students at risk. A mobile application that
allows teachers to trace out the values of these indicators on the basis of data gathered from learning
management system is designed and implemented. The application captures, analyses and visualizes
data in order to help teachers identify the opportunities for improvements of the quality of courses and
enhancing of performance of their students. Using the application, teachers are able to keep track on
activity and progress of their students, adherence to the learning schedule, as well as to quickly
identify students who are at risk for failing or dropping out at an earlier stage than it otherwise would
be possible.
Keywords: Learning Analytics, student big data, mobile app, teacher.
1 INTRODUCTION
Learning Management Systems (LMS) are widely used in educational institutions. Students are
increasingly carrying out their learning online, using devices such as laptops, tablets and
smartphones. This leaves a “digital footprint”, which can be automatically analysed, and combined
with data about their backgrounds, past academic performance or their career aspirations [1]. When
conducting online courses vital pieces of data for students are stored in the LMS database, such as
students’ grades on a particular test/assignment or a whole course, duration of students’ participation
in learning activities and throughout the course, how many times students have access learning
resources and activities, how many times students have participated in communication, etc. The wide
range of data produced by participants in the learning processes led to increased interest in the
collection and analysis of data to support data-driven decision making at all levels of educational
institutions and the emerging of a new research field, called Learning Analytics. Learning Analytics
refers to the process of collecting, evaluating, analysing, and reporting organizational data for decision
making [2] and for the purpose of improving learning processes [3]. Siemens [4] defines Learning
Analytics as “the use of intelligent data, learner-produced data, and analysis models to discover
information and social connections, and to predict and advise on learning.” It helps teachers and
students to take action based on the evaluation of educational data. Learning analytics research uses
data analysis to support informed decisions made on every tier of the educational system. By using
Learning Analytics stakeholders can improve the quality of learning and digital learning resources,
improve course outcomes, improve student retention, support informed decision making, track and
predict students’ performance, identify potential issues and students at risk, understand students’
learning behaviours and develop more engaging and effective teaching and learning techniques.
Learning Analytics is a promising emerging field, but higher education institutions need to become
more familiar with methods (visual data analysis, social network analysis, semantic analysis, and
educational data mining), benefits for all levels of stakeholders (governance, institution, teacher and
studnets [5]) and challenges (tracking, collection, evaluation and analysis of data, the need for
learning environment optimization, issues concerning ethics and privacy, etc.) related to its application
[6]. The level of development of modern technologies allows stakeholders to experience the benefits
of Learning Analytics through the use of mobile and online applications that track data about their
performance in the learning process and raise awareness on the learning process [7]. Many
institutions worldwide [2, 8, 9, 10, 11, 12, 13] have already used Learning Analytics to improve the
Proceedings of INTED2019 Conference
11th-13th March 2019, Valencia, Spain
ISBN: 978-84-09-08619-1
8133
quality of learning, student success and retention, to delivery automatic and immediate feedback, and
to provide a personalised experience for students.
The paper is devoted to Learning Analytics from the teacher’s perspective. It proposes a set of
measurable indicators that Learning Analytics should provide to help teachers be more reflective in
their teaching practice, to improve the quality of education provided in their courses and relevance of
the learning materials, to discover more about students’ learning and active participation in the course,
to track and predict students’ performance, to improve students’ success rate, to control scheduling, to
identify potential issues and students at risk. The proposed indicators are specified in the case of the
most used LMS worldwide – Moodle. That is why an analysis of the big data generated in the learning
process in Moodle is done. A mobile application that allows teachers to trace out the values of these
indicators on the basis of data gathered from Moodle is designed and implemented. The application
captures, analyses and visualizes data in order to help teachers identify the opportunities for
improvements of the quality of courses and enhancing of the performance of their students. Using the
application, teachers are able to keep track on activity and progress of their students, adherence to
the learning schedule, as well as to quickly identify students who are at risk of failing or dropping out at
an earlier stage than it otherwise would be possible.
2 METHODOLOGY
The process for development of a mobile app for learning analytics includes 5 main stages:
• Stage 1. Studying teachers' opinion on useful results of their teaching practice and functional
characteristics of the developed application (see Section 3.1);
• Stage 2. Studying other applications that provide opportunities for Learning Analytics and their
measurable indicators (see Section 3.1);
• Stage 3. Developing a set of measurable indicators (see Section 3.2);
• Stage 4. Specifying the developed set of measurable indicators in the context of the LMS used
in the university – Moodle (see Section 3.3);
• Stage 5. Developing a mobile app for Learning Analytics (see Section 3.4).
3 RESULTS
The fifth stages of the methodology are described in details in the following sections
3.1 Studying teachers’ opinion and others application for Learning Analytics
In recent years, researchers and educators have begun to explore how they can use new sources of
data on students and their learning, together with predictive analytics techniques, to improve many
aspects of the educational experience [1]. Learning Analytics (from the teacher’s perspective) are
important for education and can improve the quality of education before it [12,13]:
• helps teachers to predict students’ performance and to better understand learning processes;
• helps teachers to increase students’ retention rate and to improve students’ success rate;
• helps teachers to improve the quality of their courses;
• helps teachers to enhance the learning and assessment content and activities that are provided
to students;
• helps teachers to do research on hypothesizes by collecting, analysing, and visualizing the right
data in an appropriate way;
• helps teachers to find out how well the overall instructional design is appreciated.
Other Learning Analytics tools have been considered [12, 13, 14, 15] and a study among teachers has
been conducted in order to be identified indicators that provide useful information to teachers, allowing
them to make informed data-driven decisions and improve the quality of courses.
The results of the conducted study among teachers who are motivated to evaluate their courses have
shown that teachers would like the developed application to allow them to:
8134
• see how students are taking their course in order to identify issues and improve their teaching
and curriculum design by adding more focus on a specific focus or redesigned a course module;
• monitor students’ performance while the teaching module is taking place;
• monitor if students access the learning content and adhere the schedule;
• analyse their lesson plans and the curriculum;
• reveal more about their students' learning;
• see who students are at risk in order to provide additional support to these students to improve
their learning experiences and results;
• what their students’ active participation is compared to those of other students in the course and
students with excellent grades from the previous year;
• what their students’ success rate is compared to those of other students in the course and
students with excellent grades from the previous year;
• whether their students adhere to the learning schedule.
3.2 A set of measurable indicators for Learning Analytics from a teacher’
perspective
The advancement of technology has provided the opportunity to track and store students’ learning
activities as big data sets within different systems [6]. These data can be automatically analysed, and
combined with data about students’ backgrounds, past academic performance or their career
aspirations [1]. LMSs play a central role in each Learning Analytics tool. Most of the most widely used
LMSs have monitoring and reporting tools that are designed to collect, analyse and visualize data in a
tabular form [15, 16], but they do not help teachers to answer their questions about student
performance, success rate, etc.
In order to allow teachers to track their students’ activity and success rate during training, to monitor if
the students adhere to the learning schedule, to see who students are at risk additional reports have
to be developed. For this purpose, on the basis of the analysis of the results from the conducted
survey among teachers a hierarchical system of measurable indicators is defined. These indicators
can be described as specific calculations with corresponding visualizations. Learning Analytics
Indicators (LAI) are grouped into 2 levels. Level 1 contains three indicators – 1. Student Active
Participation, 2. Control of Scheduling and 3. Student Success Rate. Each of these LAI contains
one or more indicators of Level 2 (see Table 1.).
Table 1. Learning Analytics Indicators
Indicator - Level 1
Indicator - Level 2
1. Student Active Participation
1.1. Learning activities for communication and collaboration
1.2 Learning activities for assessment
1.3. Learning resources
1.4. Course learning
2. Control of Scheduling
2.1. Access to learning materials
2.2. Completion of learning activities
2.3. Student progress
3. Student Success Rate
3.1. Assessment trends in learning activities
3.2. Assessment trends and student success rate
The first indicator of Level 1 1. Student Active Participation groups 4 LAI of Level 2 that allow
teachers to monitor:
8135
• student’s active participation in learning activities for communication and collaboration and to
compare results with the activity of other students and students from previous years (Indicator
1.1);
• student’s active participation in learning activities for assessment and to compare results with
the activity of other students and students from previous years (Indicator 1.2);
• number of visits of every student to learning resources (by weeks and all the time) and
comparison of results with the activity of other students and students from previous years
(Indicator 1.3);
• number of visits of every student to a course (by weeks and all the time) and to compare results
with the activity of other students and students from previous years (Indicator 1.4).
The second indicator of Level 1 2. Control of Scheduling contains 3 indicators of Level 2 that allow
teachers to monitor:
• learning plans and whether every student read learning materials on-time, late, or not at all
(Indicator 2.1);
• learning plans and whether every student complete learning activities on-time, late, or not at
all (Indicator 2.2);
• student progress in learning activities for every student in the course (Indicator 2.3).
The third indicator of Level 1 3. Student Success Rate groups 2 LAI of Level 2 that allow teachers to
monitor:
• assessment trends in each one of the learning activities in the course for every student in the
course and to compare results with the results of other students and students from previous
years (Indicator 3.1);
• assessment trends for every student in the course, to compare results with the results of other
students in the course and results of students from previous years and quickly identify students
who might be struggling or improving over time
3.3 Measurable indicators in Moodle
Much of the data that can be used for Learning Analytics comes from the LMSs. In each LMS data can
be collected from different kinds of student activities, such as uploading assignments, taking quizzes,
participating in discussion forums, reading learning materials, etc. This data can be used for extraction
of valuable information, which can help teachers to improve the quality of learning materials, improve
course outcomes, improve student retention, support informed decision making, track and predict
students’ performance, identify potential issues and students at risk.
Because of this, the LAI mentioned above are specified in the term of one of the most widely used
LMS (used at the University of Plovdiv) as a specific calculation and an analysis of data stored in its
database has been made. The database of Moodle has around 200 tables. When many students use
the system they genera a huge amount of data that can be defined as big data. Data about courses,
learning resources and activities, users and all activities that users perform within the system are
stored in 75 tables [17]. The analysis of data stored in these 75 tables allows us to define which of the
stored data can be useful for teachers to improve the course quality and help students to achieve
better results. Part of these data are generated by students during their training (number of views of
learning materials and activities, submissions, test results, etc.) and the rest - by teachers when they
assess student activities (assignments, test, etc.).
The specified indicators are collecting data of students to present them to teachers. Data for each
indicator of Level 2 are obtained through extraction and systematization of big data generated by
students or/and teachers during training for each specific resource and activity (in the terms of
Moodle) in the course or for the whole course.
The first indicator of Level 2 assesses the students’ active participation. The data for the assessment
of the students’ active participation in activities for communication and collaboration (Indicator 1.1) in
Moodle can be collected through retrieving data for students’ participation in all kinds of learning
activities that can be used for communication and collaboration (Forum, Chat and Wiki). For each one
of them measurable indicators are defined data for which can be extracted from the Moodle database:
8136
- Forum:
o Number of views of discussions by the student
o Average number of views of discussions by students in the course
o Average number of views of discussions by excellent students from the previous year
o Number of discussions added by the student
o Average number of discussions added by students in the course
o Average number of discussions added by excellent students from the previous year
o Number of comments read by the student
o Average number of comments read by students in the course
o Average number of comments read by excellent students from the previous year
o Number of comments added by the student
o Average number of comments added by students in the course
o Average number of comments added by excellent students from the previous year
- Chat:
o Number of messages sent by the student
o Average number of messages sent by students in the course
o Average number of messages sent by excellent students from the previous year
o Number of sessions views by the student
o Average number of sessions views by students in the course
o Average number of sessions views by excellent students from the previous year
- Wiki:
o Number of views of the Wiki by the student
o Average number of views of the Wiki by students in the course
o Average number of views of the Wiki by excellent students from previous year
o Number of wiki pages added by the student
o Average number of wiki pages added by students in the course
o Average number of wiki pages added by excellent students from previous year
o Number of views of wiki pages by the student
o Average number of wiki pages by students in the course
o Average number of wiki pages by excellent students from previous year
The indicator 1.2 Learning activities for assessment supports teachers to monitor how active
students are in different kinds of learning activities in Moodle. For each kind of activity (Database,
Workshop, Glossary, Lesson, Quiz, External tool, Assignments) are determined specific data that can
be extracted from Moodle database:
- Database
o Number of views of the Database by the student
o Average number of views of the Database by the students in the course
o Average number of views of the Database by excellent students from the previous year
o Number of records added by the student
o Average number of records added by students in the course
o Average number of records added by excellent students from the previous year
- Workshop
o Number of views of the Workshop by the student
o Average number of views of the Workshop by students in the course
o Average number of views of the Workshop by excellent students from previous year
8137
o Number of works submitted by the student
o Average number of works submitted by students in the course
o Average number of works submitted by excellent students from the previous year
o Number of works graded by the student
o Average number of works graded by students in the course
o Average number of works graded by excellent students from the previous year
- Glossary
o Number of views of definitions in the dictionary by the student
o Average number of views of definitions in dictionary by students in the course
o Average number of views of definitions in dictionary by excellent students from the previous
year
o Number of definitions added to the dictionary by the student
o Average number of definitions added to the dictionary by students in the course
o Average number of definitions added to the dictionary by excellent students from the
previous year
o Number of definitions added by the student that are approved by the teacher
o Average number of definitions added by students in the course that are approved the
teacher
o Average number of definitions added by excellent students from the previous year and
approved by the teacher
- Lesson
o Number of views of the Lesson by the student
o Average number of views of the Lesson by students in the course
o Average number of views of the Lesson by excellent students from the previous year
o Number of pages of the lesson visited by the student
o Average number of pages of the lesson visited by students in the course
o Average number of pages of the lesson visited by excellent students from the previous year
o Duration of participation of the student in the activity
o Average duration of participation of students in the course in the activity
o Average duration of participation of excellent students from the previous year in the activity
- Quiz
o Number of attempts that students have to solve the Quiz
o Number of attempts made by the student to solve the Quiz
o Average number of attempts made by students in the course to solve the Quiz
o Average number of attempts made by excellent students from the previous year to solve the
Quiz
o Time for which the student has solved the Quiz
o Average time for which students in the course have solved the Quiz
o Average time for which excellent students from the previous year have solved the Quiz
- External tool
o Number of views of the External tool by the student
o Average number of views of the External tool by students in the course
o Average number of views of the External tool by excellent students from the previous year
o Number of activities carried out within the External tool
- Assignments
o Number of views of the Assignment by the student
8138
o Average number of views of the Assignment by students in the course
o Average number of views of the Assignment by excellent students from the previous year
o Number of submissions added by the student
o Average number of submissions added by students in the course
o Average number of submissions added by excellent students from the previous year
The next indicator 1.3. Learning resources allows teachers to monitor how much time students read
learning resources in Moodle (Folders, Pages, URLs, Files, IMS content packages, Books) and to
compare the student’s active participation with the active participation of other students (from the
current year or student with excellent grades from previous years). The data for this indicator that can
be extracted from the Moodle database and analysed include number of views of learning resources
by the student, average number of views of learning resources by students in the course, average
number of views of learning resources by excellent students from the previous year.
The last indicator from this category 1.4. Course learning supports teachers to monitor how active
students are in the course. The active participation of each student in the course is measured through
calculating the number of course views by the student (for each week or a chosen time period), time
spent in the course by the student (for each week or a chosen time period), average number of course
view by students in the course (for each week or a chosen time period), time spent in the course by
students in the course (for each week or a chosen time period). These values give the teacher the
opportunity to see the calculated values for the chosen student as well as to compare him or her
results with the average values for all enrolled students (from the current year).
The second indicator of Level 1 2. Control of Scheduling contains 3 indicators of Level 2. The first
one 2.1. Access to learning materials allows teachers to monitor whether students read learning
materials uploaded in Moodle (Folders, Pages, URLs, Files, IMS content packages, Books) on-time,
late, or not at all. For each learning material (resource in the terms of Moodle) from the database can
be extracted data for the schedule (time period in which the resource must be read by students), date
and time when the student first accessed the learning material, date and time when the student last
accessed the learning material, numbers of views of the learning material by the student. These
values can be selected for a chosen student and/or resource as well as for all students enrolled in the
course (from the current year) and/or all resources added in the course.
The second indicator 2.2. Completion of learning activities supports teachers to track whether
students complete learning activities (Assignments, Feedbacks, Databases, Quizzes, Lessons, Wikis,
Workshops, Glossaries) on-time, late, or not at all. For each learning activity from the Moodle
database can be extracted data for the schedule (time period in which the activity must be completed
by the student), deadline for activity completion, date and time when the student completed the
activity, numbers of days of delays for activity completion. These values can be extracted for a chosen
student and/or activity as well as for all students enrolled in the course (from the current year) and/or
all activities which students have to complete during the training.
The third indicator 2.3. Student progress allows teachers to monitor student progress in learning
activities for each student in the course. For the assessment of this indicator from the Moodle
database can be extracted data for the number of tasks for completion for each student enrolled in the
course and the status of each activity (In progress, Completed, Deadline approaching).
The last indicator from Level 1 groups 2 indicators from Level 2. The first one 3.1. Assessment
trends in learning activities gives teachers the opportunity to monitor assessment trends in learning
activities from different kinds (Assignments, Databases, Quizzes, Lessons, Workshops, Glossaries) in
the course for every student in the course and to compare results with the results of other students
and students from previous years. These trends in Moodle can be monitored through the extraction of
the necessary data and calculation of the average grade of the student, average grade of students in
the course during the current year, average grade of students in the course during the previous years.
These data allow teachers to take measures if the student’s average grade until now is below the
average grade in order to improve the student’s final grade.
The second indicator 3.2. Assessment trends and student success rate allows teachers to monitor
students’ assessment trends for every student in the course, to compare results with the results of
other students in the course and results of students from previous years and quickly identify students
who might be struggling or improving over time. For this purpose, from the Moodle database can be
extracted data for student’s grades and calculating the average grade of the student (during the
8139
current and the previous weeks or a chosen time period), average grade of students in the course
(during the current and the previous weeks or a chosen time period), average grade of the student in
the course (until now), average grade of the student (in all courses), average grade of students in the
course (until now), average grade of students from previous years
3.4 Mobile APP for Learning Analytics
On the basis of the analysis of data stored in the Moodle database and the defined hierarchical
system of LAI for systematization of this data a special Learning Analytics mobile application, is
designed and implemented. The development of the Mobile APP required the solution of some
problems related to the following main technological considerations [18]:
• Data collection - how the organization obtains original data for storage, processing and
reporting in the analytics tool;
• Data storage - the environment used to maintain an organization’s learning analytics data;
• Data processing - the actions taken on stored data to transform them into business intelligence
for analysis;
• Data reporting - the formal presentation of the results of a processed request.
The Mobile APP gathers data from different students’ activities when they interact with learning
resources and activities in Moodle, analyses that data, and generates reports in order to help teachers
to reflect on the impact of their teaching method on their students’ performance and draw conclusions
about the effectiveness of their teaching in order to improve the quality of their courses and students’
success rate.
The architecture of the Mobile APP (see Figure 1) includes 8 components. User is able to interact the
system through the Scheduling GUI and Android APP to view already gathered statistics. By using
Scheduling GUI user can add a new indicator, delete an indicator or update indicator properties such
as an interval of scheduled data retrieval or a template of select query at any time. User can pause
scheduling for an indicator. The CRON Scheduling Service gathers data from Moodle server by using
Moodle’s REST API and sends the gathered data to the Statistical Server to be stored into its
Statistical DB. The Scheduling Service is also responsible to synchronize the metadata for the
indicators with the Statistical Server by sending new metadata through the ST.S. REST API. The
Mobile (Android) App communicates directly to the Statistical Server through its ST.S. REST API. The
GUI of the Mobile APP is dynamically generated based on the Indicators Metadata in the Statistical
DB. Scheduling DB contains metadata, which is specifically related to scheduling, such as SELECT
query template, user input parameters, scheduling interval, start datetime, end datetime, isActive, etc.
Statistical DB contains already gathered data for the indicators, indicators names and descriptions,
type of chart to be visualized for each indicator, etc.
Figure 1. Architecture
Moodle Server
Statistical Server
Statistical DB
Moodle DB
And roid A PP
Scheduling DB
CRON Scheduling Service
Scheduling GUI
HTTPS
ST. S. REST API
MOODLE REST API
ST.S. REST API
8140
The Mobile APP is a graphical interactive monitoring application that provides useful visualization of
students' activities in online courses to teachers. The mobile application is simple and easy-to-use for
teachers. Teachers can use the app to examine various aspects of their students, such as the
participation in courses, reading of learning materials, submission of assignments, etc. The Mobile
APP provides comprehensive visualizations that gives an overview of a chosen student or all students
enrolled in the course. It indicates facts about the students’ active participation and success on the
basis of defined indicators, which can be described as specific calculators with corresponding
visualizations. The Mobile APP indicators are collecting and visualizing data of students to present
them to teachers. It allows teachers to generate dynamically reports for their students’ active
participation in a course and their success rate, containing values of the defined LAI (see Section 3.3)
and to compare their results with the average values for active participation and success rate of the
other students in the course and students with excellent grades from previous years. These
comparisons are helpful because they allow teachers to view if the chosen student is below or up to
the average level of other students in the course or students from previous years and can help to take
measures to increase her or him activity and success. The APP allow teachers to track whether their
students adhere to the learning schedule. They can use the APP to view details of resources and
activities already completed and grades obtained by their students. The automated alerts sent to
teachers allow them to view the students who could most benefit from their input.
To use the mobile app teachers need to log in and select the course (and the student if they want to
generate reports with data for a chosen student) for which they want to generate reports with values of
LAI for their students’ active participation, success rate or control of learning schedule. The course
names between the teachers can select are extracting from the data source (Moodle database). This
limits the user choice and thus eliminates the possibility of introducing incorrect data. Besides
selecting the course name (and eventually student for personal reports), teachers have to select report
from which of the three main sections (see Figure 2, Screen 1) they want to generate:
• Active participation - allows teachers to view what their student’s active participation in learning
activities and resources is compared to the average level of active participation of other
students in the course and students with excellent grades from previous years.
• Control of Scheduling - allows teachers to view if their students read learning
resources/activities and submit the assignment on-time, late, or not at all.
• Success Rate - allows teachers to monitor assessment trends.
Each one of these three sections contains a list of reports with names corresponding to the indicators
of Level 2 from Table 1 (see Figure 2, Screen 1) between the teachers have to select. The generated
report contains values of LAI presented in a variety of ways (including tables, charts, graphs of active
participation over time compared with others, etc.) that teachers can use to improve the quality of their
courses and their students’ success. Teachers can filter the data which report contains. The filtering of
the presented data is context-dependent according to the currently selected indicator (e.g. time period,
specific resource or activity, student’ name or all students in the course). Screen 2, Screen 3 and
Screen 4 present examples of generated reports. The first screen (Screen 3) contains a report on the
activity of the student Ivan Petrov in all assignments for the previous 5 weeks. The first chart presents
number of views of all assignments by the chosen student, average number of views of students of all
assignments by students in the course and average numbers of views of all assignment by students
who have received excellent grades in the previous year. The second chart presents number of
submissions uploaded to assignments by the chosen student, average number of submissions
uploaded to all assignments by students in the course and average numbers of submissions uploaded
to all assignment by students who have received excellent grades in the previous year. The table
shows the number of views and submission uploaded to assignment by the selected student, all
students in the course from the current year (average numbers) and students who have had excellent
grades in the previous year (average number) for each one assignment during the chosen time period
(previous five weeks and the first five weeks of the course in the previous year). The analytic results
show that the activity of the chosen is higher than the activity of other students in the course, but lower
than the activity of students who have received excellent grades in the previous year (until the same
week). These results can help teacher to take measures to help the student to increase him/her
activity in order to increase the student’s chance of getting an excellent grade. The report from Screen
4 contains a table that presents the average grades from all learning activities of each student in the
course until the chosen date. The report contains calculated average grades of all students enrolled in
the course from the current year and all students who have completed the course in the previous year.
The names of all students who have grades lower than the average grades are colored in red. These
8141
results can help teacher to identify students who have low grades and to take measures to help these
students to improve their success rate.
Figure 2. Screens of Mobile APP
4 CONCLUSIONS
Mobile APP provides information to teachers about their students’ learning activity. It allows teachers
to track their students’ activity and success rate during training and to compare them with the average
level of activity and success rate of the other students (including from previous years) in order to
increase their success as well as to track whether they adhere to the learning schedule. The
developed mobile application will be tested over the next school year. On the basis of the feedback
from teachers the functionalities of the application will be expended.
ACKNOWLEDGEMENTS
The paper is supported within the National Program “Young scientists and Postdoctoral students”.
REFERENCES
[1] N. Sclater, “Learning Analytics Explained, Routledge”; 1 edition, 290 pages, 2017.
[2] J. Campbell, P. De Blois, D. Oblinger, “Academic analytics: A new tool for a new era”, Educause
Review, Vol. 42, No. 4, pp. 40-57, 2007.
[3] M. Brown, “Learning analytics: Moving from concept to practice”. EDUCAUSE Learning Initiative,
2012, Retrieved from https://library.educause.edu/~/media/files/library/2012/7/elib1203-pdf.pdf
[4] G. Siemens et al., “Open Learning Analytics: an integrated & modularized platform”, 2011.
[5] C. Schumacher, D. Ifenthaler, “Features students really expect from learning analytics”,
Computers in Human Behavior, vol. 78, pp. 397-407, 2018.
[6] J. Avella et al., “Learning Analytics Methods, Benefits, and Challenges in Higher Education: A
Systematic Literature Review”, Online Learning, Vol. 20, No. 2, pp. 13-29, 2016.
[7] B. Tabuenca et al., “Time will tell: The role of mobile learning analytics in self-regulated learning”,
Computers & Education, Vol. 89, pp. 53-74, 2015.
[8] B. Wong, “Learning analytics in higher education: an analysis of case studies”, Asian Association
of Open Universities Journal, Vol. 12, No. 1, pp. 21-40, 2017.
[9] B. Rienties et al., “A review of ten years of implementation and research in aligning learning
design with learning analytics at the Open University UK”, Interaction Design and Architecture(s)
Journal - IxD&A, N.33, pp. 134-154, 2017.
[10] B. Dietz-Uhler, J. Hurn, “Using Learning Analytics to Predict (and Improve) Student Success: A
Faculty Perspective”, Journal of Interactive Online Learning, Vol. 12, No. 1, pp. 17-26, 2013.
8142
[11] N. Sclater, “Learning analytics: The current state of play in UK higher and further education”, Jisc,
2014.
[12] A. Dyckhoff, D. Zielke, M. Bültmann, M. Chatti, U. Schroeder, “Design and Implementation of a
Learning Analytics Toolkit for Teachers”, Educational Technology & Society, Vol. 15, No. 3, pp.
58–76, 2012.
[13] Dyckhoff, A. L., Zielke, D., Chatti, M. A., & Schroeder, U. (2011). eLAT: An exploratory learning
analytics tool for reflection and iterative improvement of technology enhanced learning. In M.
Pechenizkiy et al. (Eds.), Proceedings of the 3rd Conference on Educational Data Mining 2011
(pp. 355–356). Eindhoven, The Netherlands: International EDM Society.
[14] R. Ferguson, A. Brasher, D. Clow, A. Cooper, G. Hillaire, J. Mittelmeier, B. Rienties, T. Ullmann,
R. Vuorikari, Research Evidence on the Use of Learning Analytics - Implications for Education
Policy. R. Vuorikari, J. Castaño Muñoz (Eds.). Joint Research Centre Science for Policy Report;
2016, EUR 28294 EN; doi:10.2791/955210.
[15] C. Romero, S. Ventura, E. García, “Data mining in course management systems: Moodle case
study and tutorial”, Computers & Education, Vol. 51, No. 1, pp. 368–384, 2007.
[16] Moodle Docs, Learning analytics, Retrieved from https://docs.moodle.org/33/en/Learning_
analytics.
[17] S. Gaftandzhieva, Model and System for Dynamic Quality Evaluation in Higher Education, PhD
Thesis, Plovdiv, 2017 (in Bulgarian).
[18] V. David, “Technological Considerations in Learning Analytics”, 2005, Retrieved from
http://www.clomedia.com/2005/06/29/technological-considerations-in-learning-analytics/.
8143
