Skip to main content

Table 10 Comparison Model Performance (Facebook Dataset)

From: Text based personality prediction from multiple social media data sources using pre-trained language model and model averaging

Facebook
System Average accuracy Average F1
Tandera et al. [37] 70.40%
Zheng and Wu [42] 0.71
Tadesse et al. [36] 74.20%
Yuan et al. [41] 70.00%
Experiment model
Scenario 1–8 72.50% 0.688
Scenario 9–16 71.85% 0.677
Scenario 17–24 72.13% 0.683
Scenario 25–32 74.53% 0.718
Scenario 33–40 74.79% 0.720
Scenario 41–48 75.20% 0.723
Scenario 49–56 76.75% 0.742
  1. The highest values for the average accuracy and f1-measure for each personality model are shown in bold