![](bg2.png)
ong the course as predictors.
The rest of the paper is organized as follows. In
Section 2 we give an overview of the core social
engine, and describe the general principles of our
learning-enhanced social platform. The methodology
employed in a real testbed (two consecutive editions
of an undergraduate course on Computer Networks)
is reported in Section 3. Section 4 contains the main
results of the data mining applied to our datasets. The
proposed success/failure prediction methods are ex-
plained in Section 5. Finally, concluding remarks and
guidelines for further work are included in Section 6.
2 THE LEARNING PLATFORM
Socialwire (Sousa et al., 2016) is a SLE purposely
designed to provide a complete networked learning
paradigm, including features not available in other
SLEs. For instance, Socialwire uses games and so-
cial meritocracy as conducting threads. The software
platform is based on ELGG (Elgg), a popular engine
for developing OSNs, and allows the creation, asses-
sment and reporting of a range of collaborative activi-
ties based on social interactions among the students,
offering a reward mechanism by means of ranking
and reputation.
The platform was developed upon four blocks:
• The online social network. SocialWire leverages
on the core of ELGG for reusing the fundamental
elements of a generic OSN. Every group (class-
room group) defined in the system has its own
wall to maintain open communication among all
its members. The group can also use common
tools in the social web for its virtual classroom
activities: classroom blog, collaborative publis-
hing and document editing, creation of web pages,
social tagging, files repositories with hierarchi-
cal structure (including a viewer for images, au-
dio, video and the usual document formats), and
event calendars. All the activity unfolded in the
classroom gets eventually reflected on the public
wall, so it can be commented, highlighted or vo-
ted. Sharing videos, uploading a file, save and
send a link are extremely simple actions which the
user can invoke through an user interface delibe-
rately similar to an OSN user interface. The user-
friendliness is higher, as a bonus, and the learning
curve of the platform itself is greatly softened.
• The formal learning processes. To furnish Social-
Wire with the usual features of a LMS, we have
developed custom software modules that extend
the bare OSN based on ELGG. Specifically, there
exist modules for proposing and submitting tasks
(either online or offline), for the creation and as-
sessment of quizzes and questionnaires, for the
creation and processing of forms or polls, for buil-
ding an e-portfolio, for designing rubrics for eva-
luation, and more. Another software module gives
the teachers the possibility of structuring the lear-
ning units in their courses, for instance weekly,
monthly, by topic,... and adding to each unit as
many resources as they like.
• The informal learning processes. SocialWire
opens the possibility of carrying out other sort of
activities requiring a higher degree of social in-
teraction. This is done by means of the questions
and answers module and the contests module. Be-
sides the usual grading procedure used in formal
courses (on a numeric scale or by discrete levels),
in SocialWire the students can receive “points” or
“marks” for their works. The points accumula-
ted along the course determine their position in
the students’ ranking. This ranking serves pri-
marily to send behavioral signals to the students
about their relative performance, in a way that di-
rectly stimulates comparisons and that automati-
cally conveys the meaning of social reputation.
• The collaborative work processes. Most of the
popular software platforms for collaborative work
fail to give real, effective support for working col-
laboratively. First, the users are not given a vir-
tual workspace where direct communication and
sharing between colleagues can happen, so they
must resort to external programs to solve this (or
in extreme cases, physical meetings). Secondly,
teachers are not provided with the opportunity
to manage, coordinate, assess, evaluate, share or
communicate with the workgroups. SocialWire
does permit subgroups, i.e., smaller groups within
an existing group. The instructors are in charge of
deciding how many groups will be created, their
sizes and their membership policies, if any is due.
Every activity supported by SocialWire can be as-
signed to a group or to an individual, and in the
former case any group member is entitled to parti-
cipate in the role of group’s representative. Addi-
tionally, every subgroup is internally a group and
has a private space so that their members and the
instructors can communicate.
For the goals of this paper, two of the plugins
of SocialWire are of key importance. These are the
event collector plugin, and the event viewer plugin.
The first is a plugin that runs in the background
and records all the relevant activity of the students
(and teachers too), both the interactions between an
user and the learning objects stored in the platform
Prediction of Learning Success Via Rate of Events in Social Networks for Education
375