Malik Koné committed Feb 11, 2019 1 2 3  # Table of Contents  Malik Koné committed Feb 11, 2019 4 5 6 1. [CSEDU-2019](#orgf6d31a1) 1. [Resources and annexes to the paper "Towards Visual Explorations of Forums' Collective Dynamics in Learning Management Systems"](#org31d27d9) 1. [Images](#org55b7bb5)  Malik Koné committed Feb 11, 2019 7 8   Malik Koné committed Feb 11, 2019 9   Malik Koné committed Feb 11, 2019 10   Malik Koné committed Feb 11, 2019 11 12 # CSEDU-2019  Malik Koné committed Feb 11, 2019 13   Malik Koné committed Feb 11, 2019 14   Malik Koné committed Feb 11, 2019 15 16 17 18  ## Resources and annexes to the paper "[Towards Visual Explorations of Forums' Collective Dynamics in Learning Management Systems](tex_draft.pdf)"  Malik Koné committed Feb 11, 2019 19   Malik Koné committed Feb 11, 2019 20 21 22 23 24 25 26  ### Images The images in the paper are sometime small. We offer high enough resolution images to see the details. 1. Figure 1  Malik Koné committed Feb 11, 2019 27 28 29 30 31 32 33  ![img](images/discussion.png) Illustration of how the strength of actors' ties (or links) varies as a function of time and topic overlap. Thread 1 corresponds to actor-topic dynamic (\ref{eq:1a}) where >'s late post after >'s \nth{1} publication does not correlate strongly enough to create the link from > to >. But >'s \nth{2} post is timely enough, although not exactly on the same topic as >'s message, to create the tie drawn as a dashed arrow. In thread 2, in addition to the tie , we have a topic overlap and time proximity between > and >. This makes a the strong tie . 2. Figure 2 ![img](images/fu.png)  Malik Koné committed Feb 11, 2019 34   Malik Koné committed Feb 11, 2019 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72  iForum's Dashboard \citep{Fu2017} showing (a) overall changes of post in the forum, (b) a thread representation, (c) discussions in packed forms, (d) the social network and (e) the details of a discussion. 3. Figure 3 ![img](images/convis.png) Convis Dashboard \citep{Hoque2016} helps explore conversations. On the left, the topics found in the forum using \gls{lda} and organized hierarchically. In the middle, the colored rectangles show a sentiment analysis for each message. Each message is linked to his author place on a semi-circle and thus creating a social network. Finally, on the right, Convis display the detail of the conversation. 4. Figure 4 ![img](images/func.png) Graphical proposition for the function of the messages' interaction strength. > is the \\internal'' strength of two messages based on content, time and social network structure. > is \\external'' requirement, it is a parameter set by the observer. 5. Figure 5 ![img](images/cycles.png) Interactions cycles built from a bi-party actor-topic graph Thread 3 and 4 are transformed to an actor-actor graph. Dotted arrows denotes weaker links. 6. Figure 6 ![img](images/pipeline.png) Data Analysis cycle. 7. Figure 7 ![img](images/dynco_portrait.png) Visualizations from the FFL dataset. 8. Figure 8 ![img](images/uvci_portrait.png) Detail of \gls{vuci} conversation taking place in 2 hours. Each circle is a message, and hovering over them brings up its content. The circle's size is proportional to their content's length. Message are layered vertically by actors. On the left is an indication of the actors total messages count. 9. Figure 9 ![img](images/evolution.png) At the top (a) is half of compound yearly actor-actor network. The three bottom images (b), (c) and (d) are closeup around actor 642 during the quarters of the year.  Malik Koné committed Feb 11, 2019 73