Group Lifecycle dichotomy -Cascade Tree Pattern Depth=1 Depth=2 . Subtree size: The size of sub-cascade .Depth: The depth of invitation .Wiener Index: Average distance between two nodes
11 Group Lifecycle Dichotomy – Cascade Tree Pattern •Subtree size: The size of sub-cascade •Depth: The depth of invitation •Wiener Index: Average distance between two nodes Depth=1 Depth=2
Group Lifecycle Dichotomy--Cascade Tree Pattern >10% of users have subtree size >=10 0° 10% of invitations occur at >=3 10%with W-index >=2 Short-term Short-term Long-term Short-term 二 百号 fa o only -2% have substree size >=hoi Only 1% occur at >=3 2343678。002314562÷k Subtree size Wiener Index (b) Subtree size (c)Depth (d)Wiener index · For node c 8OOO · Subtree size:3 De pth: 2 For the left example: Wiener index: 2
12 10% of invitations occur at >=3 Only 1% occur at >= 3 10% with W-index >= 2 99% with W-index < 2 Group Lifecycle Dichotomy—Cascade Tree Pattern >10% of users have subtree size >= 10 Only ~2% have substree size >= 10 • For node C • Subtree size: 3 • Depth: 2 • For the left example: •Wiener index: 2
Group Lifecycle Dichotomy Features Group Level For group C at time T The number of open triads at T and at the setting up of group Group Structure The number of closed triads at T and at the setting up of group Wiener index Cascade Tree Number of members whose depthequal to k, k=1, 2,. 9 Number of members who stated their gender to be x Demographics Entropy of member's gender
13 Group Lifecycle Dichotomy — Features Group Level: For group C at time T Group Structure The number of open triads at T and at the setting up of group. The number of closed triads at T and at the setting up of group. Cascade Tree Wiener index. Number of members whose depth equal to k, k = 1,2,...,9. Demographics Number of members who stated their gender to be X. Entropy of member’s gender
Group Lifecycle DIchotomy Prediction SVM 10-fold Cross validation Features AUC Precision Recal F1 All Features 66.62 57.66 60.32 -Structure 64.75 62.83 61.04 cascade 65.36 64.49 47.67 54.82 Demographics 65.24 57.35 65.71 6125 +Structure 64.21 61.98 42.51 5043 +Cascade 61.23 57.35 65.71 61.25 +Demographics 62.77 63.18 41.41 50.03 Task 1: Group Separability: Predict groups' lifespan Task 2: Early Prediction: Can we predict the group lifecycle in early stage
14 Group Lifecycle Dichotomy— Prediction SVM 10-fold Cross Validation Features AUC Precision Recall F1 All Features 66.62 63.23 57.66 60.32 -Structure 64.75 59.36 62.83 61.04 -Cascade 65.36 64.49 47.67 54.82 -Demographics 65.24 57.35 65.71 61.25 +Structure 64.21 61.98 42.51 50.43 +Cascade 61.23 57.35 65.71 61.25 +Demographics 62.77 63.18 41.41 50.03 • Task 1: Group Separability: Predict groups’ lifespan. • Task 2: Early Prediction: Can we predict the group lifecycle in early stage. All Features 66.62 63.23 57.66 60.32 +Cascade 61.23 57.35 65.71 61.25
Group Lifecycle DIchotomy Prediction SVM 10-fold Cross validation Features AUC Precision Recal F1 1 hour 57.95 54.16 5545 65.08 61.92 53.38 57.34 5 days 6546 54.11 58.01 10 days 6557 56.81 59.51 20 days 65.76 62.78 56.56 59.51 1 month 66.62 63.23 57.66 60.32 Task 1: Group Separability: Predict groups'lifespan Task 2: Early Prediction: Can we predict the group lifespan in early stage
15 Group Lifecycle Dichotomy— Prediction SVM 10-fold Cross Validation • Task 1: Group Separability: Predict groups’ lifespan. • Task 2: Early Prediction: Can we predict the group lifespan in early stage. Features AUC Precision Recall F1 1 hour 57.95 54.16 56.80 55.45 1 day 65.08 61.92 53.38 57.34 5 days 65.46 62.52 54.11 58.01 10 days 65.57 62.48 56.81 59.51 20 days 65.76 62.78 56.56 59.51 1 month 66.62 63.23 57.66 60.32 1 day 65.08 61.92 53.38 57.34 1 month 66.62 63.23 57.66 60.32