Exploring Social Network Analysis in Blended Learning Teacher Training Programs

Abstract

Learning Analytics is an educational application of web analytics and it is used to analyze the learners’ activities on educational platforms, in order to predict their behaviour. Learning Analytics reflects a field at the intersection of numerous academic disciplines and is using different methods like: statistics, visualizations, data/web mining, and social network analysis. Social network analysis aim is to discover patterns in individual interactions. Network analysis is based on the intuitive notion that these patterns are important attributes of the individuals’ lives. The social network analysis can be made with different software applications and it’s very important to support networked learning. Learning Analytics tools for social network analysis are providing a framework for interpreting and developing an understanding of the observed patterns of exchanges that occur between social actors. The on-line / blended educational programs from the last decades have collected an enormous quantity of data. These data include initial evaluation information, data from the training process and results of the training program. These data can be used to validate the learning analytics theory. Since the definition and purpose of learning analytics is still disputed, comparing the predictions results obtained on the basis of initial data with the final results obtained by learners can contribute to the validation of such applications. This article present the findings and conclusions obtain after analyzing series of forum posts on the educational platforms used in teachers training programs.

Keywords: Learning analyticssocial network analysisteachers trainingeducational platforms

Introduction

Learning analytics is an educational form of web analytics that aim to measure, collect, analyze and

report data about learners and their context in order to optimize the environment in which occur.

According to Ferguson (2012), “learning analytics is an emerging field in which sophisticated analytic

tools are used to improve learning and education. It draws from, and is closely tied to, a series of other

fields of study including business intelligence, web analytics, academic analytics, educational data

mining, and action analytics”.

Business Intelligence focuses on computational tools to improve organizational decision-making

through effective fusion of data collected via various systems. This term is well-known for

transforming big quantity of data into decision making capabilities.

Data Mining is the field concerned with employing large amounts of data to support the discovery

of novel and potentially useful information. From data mining was developed the field of Educational

Data Mining (EDM) “an emerging discipline, concerned with developing methods for exploring the

unique types of data that come from educational settings, and using those methods to better understand

students, and the settings which they learn in ” (Baker, & Yacef, 2009) cited by Buckingham, &

Ferguson (2012).

Even if some authors are considering that Learning Analytics and Knowledge ( LAK ) and

Educational Data Mining ( EDM ) are similar fields, there are many differences between the two fields.

Siemens & Baker (2012) made a comparison of the LAK and EDM. EDM has strong origins in

educational software and student modelling, has a greater focus on automated adaption and use

technique and methods like: classification, clustering, Bayesian modelling, relationship mining,

discovery with models, visualization. LAK has stronger origins in semantic web, intelligent

curriculum, outcome prediction, systemic interventions, has a greater focus on informing and

empowering instructors and learners and use techniques and methods like: social network analysis,

sentiment analysis, influence analytics, discourse analysis, learner success prediction, concept analysis,

sense making models.

Dringus (2012) consider that Learning Analytics require a set of conditions when are applied in

online courses: must obtain meaningful data, must have transparency, must yield from good

algorithms, must lead to responsible assessment and effective use of the data trail, must inform process

and practice.

Social Network Analysis

Networked learning involves the use of ICT to bring together learners, tutors, learning communities

and educational materials. “Social network analysis is a perspective that has been developed to

investigate the network processes and properties of ties, relations, roles and network formations, and

to understand how people develop and maintain these relations to support learning” (Haythornthwaite,

& de Laat, 2010) cited by Buckingham, & Ferguson (2012).

The results of a social network analysis might be used to: (a) identify the individuals and teams that

play an important role; (b) discover information disturbs, isolated individuals and teams; (c) emphasize

opportunities to accelerate knowledge flows across functional and organizational boundaries; (d)

strengthen the efficiency and effectiveness of existing, formal communication channels. (e) increase

awareness on the importance of informal networks. (f) mutual support; (g) improve innovation and

learning; (h) improvement strategies (Serrat, 2010).

Social network analysis is a useful tool for investigative online learning because of its focus on the

change of interpersonal relationships, and offers the potential to recognize interventions that are

possible to increase the potential of a network to support the learning of its actors by relating them to

contacts, resources and ideas.

Methodology

Results and discussions

SNAPP software was used to analyze several discussion forums from the educational platforms of

the three projects mentioned above. An attempt was made to identify disconnected learners, those with

outstanding performance, information brokers and internal groups. SNAPP statistics is displaying the

list of forum participants, beginning with the most active users and ending with the less active users of

the analyzed forum.

To identify the disconnected learners, most active learners and learning groups inside the course, it

was analyzed the social network diagram. The disconnected users are represented by nodes at the edge

of the chart. Central node represents the information-broker in that forum and the interconnecting lines

are marked with the number of posts of those users.

Using the same methodology, several discussion forums from the ForEdu, EduTic and ProWeb

projects were analyzed. For the two projects (ForEdu and EduTic), it was compared the list of the most

active users and the list of the less active users with their learning results in the frame of the teaching

program. It was noticed that the results do not show the real relationship between the data presented in

the social network diagram and the learners’ final course results. Although, it was confirmed the initial

theory that usually the disconnected users (from the diagram) are obtaining weaker results, there are

also contradictory situations.

Conclusions

During the research, some challenges and issues were identified: technical issues on running the

SNAPP software, but also challenges for correct interpretation of the obtained data. Even if the used

educational platform was Moodle, the SNAPP software didn't work on the data recorded in the forums

of the ProWeb Project. The application is parsing the ProWeb discussion forums but it is reporting zero

posts.

Also, it was identified a number of difficulties in using application analysis software. In large

forums it is complicated to analyze the social network diagram. Using too many forums it will make

very difficult the analysis.

The results obtained are not very conclusive. In general, the active students in the forums obtained

good evaluation results and some inactive students didn’t finish the training program. There are also an

important number of students inactive in forums who obtained good results at final evaluations and

they completed the training program. This can be explained by the profile of the Romanian teachers.

They have to apply for teacher training programs in order to obtain the required number of credits and

they do not have time also for course additional activities. For these reasons, they are focused on

accomplishing the tasks and assignments, and not getting involved in forums’ discussions.

It can be noticed that in order to obtain better results, the social network analysis must be combined

with some other learning analytics techniques.

Acknowledgements

This work was funded through the Seventh Framework Programme Project “ENGAGE - Equipping the Next Generation for Active Engagement in Science Project” - a coordination and support action under FP7-SCIENCE-IN-SOCIETY-2013-1, ACTIVITY 5.2.2 “Young people and science” - Topic SiS.2013.2.2.1-1: Raising youth awareness to Responsible Research and Innovation through Inquiry Based Science Education. This project has received funding from the European Union’s Seventh Framework Programme for research, technological development and demonstration, under grant agreement no 612269. The support offered by the European Commission, through the project mentioned above, is gratefully acknowledged.

References

1. Baker, R.S.J.D., & Yacef, K. (2009). The state of educational data mining in 2009: A review and future visions. Journal of Educational Data Mining, 1(1), 3-17.
2. Buckingham Shum, S., & Ferguson, R. (2012). Social Learning Analytics. Educational Technology & Society, 15(3), 3-26.
3. Dawson, S., Bakharia, A., & Heathcote, E. (2010). SNAPP: Realising the affordances of real-time SNA within networked learning environments. Paper presented at the Networked Learning Conference 2010, Aalborg, Denmark.
4. Dringus, L.P. (2012). Learning Analytics Considered Harmful. Journal of Asynchronous Learning Networks, 16(3), 87-100.
5. Ferguson, R. (2012). The State of Learning Analytics in 2012: A Review and Future Challenges. Technical Report. Knowledge Media Institute: The Open University, UK. http://kmi.open.ac.uk/publications/pdf/kmi-12-01.pdf
6. Haythornthwaite, C., & de Laat, M. (2010, May). Social networks and learning networks: Using social network perspectives to understand social learning. Paper presented at the 7th International Conference on Networked Learning, Aalborg, Denmark.
7. Petrescu A.M.A., Gorghiu L.M., Dumitrescu, C. (2015). The ENGAGE Project - A Facilitator Context for Promoting Responsible Research and Innovation in Science Lessons. Central & Eastern European LUMEN Conference: LUMEN NASHS 2015: Chisinau, Republic of Moldova: 11-13 September 2015.
8. Serrat, O. (2010). Social network analysis. Washington, DC: Asian Development Bank.
9. Siemens, G., & Baker, R.S. (2012, April). Learning analytics and educational data mining: towards communication and collaboration. In: Proceedings of the 2nd international conference on learning analytics and knowledge (pp. 252-254). ACM.