Inside forum posts – politics, networks, sentiment and words! Inspired by @phillipdawson, @shaned07, and @indicoData #moodle #learninganalytics

Enhanced communication has long been championed as a benefit of online learning environments, and many educational technology strategies will include statements around increased communication and collaboration between peers. So in thinking towards an engagement metric for my current project and the need to get inside activities for my, in progress, PhD proposal exploring forum use is one of the more interesting analytics spaces within the LMS. I’ve used three techniques for my initial analysis: (1) a look at post and reply counts inspired by @phillipdawson and his work on the Moodle engagement block, (2) social network analysis inspired by a paper by @shaned07 on teacher support networks; and (3) sentiment and political view analysis provided by @indicoData as an introduction to text mining.

I’ll start with sharing the visualisations and where these might be useful and then finish with details of how I coded these.

Forum posts

Total weekly forum posts by student

Following Phillip Dawson’s work on the engagement block for Moodle, I decided to look into two posting patterns: (1) posts over time; and (2) average post word count. The over time analysis (above) compares the weekly posting pattern of each student in a group. For most students replies to peers and teachers are “in phase” suggesting that when they are active they discuss with the entire group and so learning design might focus on keeping them active. One can also notice that those who only reply to peers appear to have much lower overall post activity, which in the original engagement block would place them at-risk – learning design may consider teacher-led interventions to understand whether discussions with the teacher impact their overall activity. The average word count analysis (below) reinforces the latter case where those demonstrating that those who only reply to peers infrequently post shorter replies. Conversely those who post infrequent lengthy posts tend to target the teacher and do not follow up with many further replies discussion. There is some suggestion of an optimal word count around 75-125 for forum posts that might warrant further investigation.

Forum Posts

Social Network Analysis

Social Network Analysis

The network diagram (above) confirms what was emerging in the post analysis: that a smaller core of students (yellow circles) are responsible for a majority of the posts, and further reveals the absolute centrality of the teacher (blue circle) that highlight how important teacher-led interventions may be to this group. This is probably not surprising although the the teacher may use this to consider how they might respond more equally to the group – here the number of replies is represented by increasing thickness of the grey edges and they appear to favour conversations in the lower left of the network. A similar theme is explored by Shane Dawson (2010) in “‘Seeing’ the learning community”. One can understand this further by plotting eigenvalue centrality against betweenness centrality (below) where a student with high betweenness and low eigenvalue centrality may be an important gatekeeper to a central actor, while a student with low betweenness and high eigenvalue centrality may have unique access to central actors.


Content Analysis

Sentiment analysis

Text analysis of forums provides a necessary complement to the above analysis, exploring the content within the context. I have used the Indico API to aid my learning of this part of the field rather than try to build this from scratch. The sentiment analysis API determines whether a piece of text was positive or negative in tone and rates this on a scale from 0 (negative) to 1 (positive). Plotting this over time (above) provides insights into how different topics might have been received with this group showing generally positive participation, although with two noticeable troughs that might be worth some further exploration. The political opinion API scores political leaning within a text on a scale of 0 (neutral) to 1 (strong). Plotting this for each user (below) shows that more politicised posts tend to be conservative (unsurprising) although there is a reasonable mix of views across the discussion. What might be interesting here is how different student respond to different points of view and whether a largely conservative discussion, for example, might discourage contribution from others. Plotting sentiment against libertarian leaning (below2) shows that participants are, at least, very positive when leaning towards libertarian ideology, though this is not the only source of positivity. Exploring text analysis is fascinating and if projects such as Cognitive Presence Coding and the Quantitative Discourse Analysis Package make this more accessible then there are some potentially powerful insights to be had here. I had also hoped to analyse the number of external links embedded in posts following a talk by Gardner Campbell I heard some years ago about making external connections of knowledge, however the dataset I had yielded zero links, which while informative to learning design is not well represented in a visual (code is included below).
Political leaning

Libertarian sentiment

Continue reading


Analysing Social Learning (#LAK12)

Dawson (2010) concludes that the value of learning analytics is to provide relevant and real-time visualisation that can assist staff to align their pedagogical practices more fully with the learning needs of all their students.

In an interesting webinar, Shane Dawson suggested that the VLE can be generalised into two tools: content page or discussion. Content is typically analysed via  session counts, dwell time, and downloads and discussions provide metrics relating to posts, replies, and views (modelled via Social Network Analysis (SNA)). I would adapt this to suggest that all activities in the VLE be viewed as discussions. Giest (2010) argues that interaction can be concrete and direct as in an online forum, but can also be abstract and indirect where the interactions or cultural tools of activity are represented in materialised forms such as content. In the hypermedia learning environment seeing activity as interactive (social) allows consistent analysis: while traditional hand-outs might show teacher-centric interactions, student-created content or collaborative Wikis may reveal different learning networks.

Some of the interesting findings that Dawson (2010) made were that students tend to interact with those of a similar ability, forming clusters of high and low performing learners. One explanation proposed was how this could represent  an effect of the Vygotskian zone of proximal development – learners gravitate within their zone and so engage with discussions at similar development levels. One might see this as an example of interaction creating conditions to identify zones (Chaiklin, 2003), where it is instruction that should create the zones (Geist, 2010). Dawson’s analysis finds a phenomenon inconsistent with this where staff interventions tend to gravitate towards the high performing networks.

Teaching staff were positioned in 81.7% of the high-performing and 34.61% of the low-performing student networks (pg. 746) and thus may be further restricting educational opportunities. One reason proposed was that in pursuing the values of a learning community it was often assumed that low end questions would be answered by other students. Whereas the tutor focused on the high performers because the questions were more difficult and so they felt more inclined to intervene. Rather than a shared project of community-wide learning students seem motivated to form networks that best enhance their individual grade performance (ego-centric).

One solution might be to use the SNA to identify peer-mediated instruction interventions (Fuchs & Fuchs, 2009). Where in practice peer groups contain a range of competency levels, ideas, conceptions, misconceptions and areas of expertise, learners can benefit from both the giving and receiving of ideas, embodied in different ways in both Vygotskian and Piagetian perspectives on social constructivism (Webb and Mastergeorge, 2003).

When designing successful social interactions and understanding the relation of technology to culture it is suggested that the only way to define the technological effects of the Internet is to build the Internet (Poster, 1995). Responsive feedback via SNA has shown how effective good visualisations of data can be in revealing these effects and allowing tutors to rebuild interactions or interventions.


Chaiklin, S. (2003). The Zone of Proximal Development in Vygotsky’s Analysis of Learning and Instruction. In A. Kozulin, B. Gindis, V. S. Ageyev, & S. M. Miller (Eds.), Vygotsky’s Educational Theory in Cultural Context (pp. 39-64). Cambridge: Cambridge University Press.

Dawson, S. (2010). “Seeing” the learning community: An exploration of the development of a resource for monitoring online student networking. British Journal of Educational Technology, 41(5), 736-752.

Fuchs, D., & Fuchs, L. S. (2009). Peer-mediated instruction. Better: Evidence-based Education, 1(1), 18-19.

Giest, H. (2010). The Formation Experiment in the Age of Hypermedia and Distance Learning. In B. van Oers, W. Wardekke, E. Elber, & R. van der Veer (Eds.), The Transformation of Learning [Kindle Edition]. Cambridge: Cambridge University Press.

Poster, M. (1995). Postmodern Virtualities. The Second Media Age. Blackwell.

Webb, N., & Mastergeorge, A. (2003). Promoting effective helping behavior in peer-directed groups. International Journal of Educational Research, 39(1-2), 73-97.