Update README.md
Browse files
README.md
CHANGED
|
@@ -8,7 +8,7 @@ The accuracy reaches 79%, and F1 score is 78%. Both are much higher than the sim
|
|
| 8 |
Due to the fact that the output values are continuous, it is better to use mean squared errors or mean absolute error to evaluate the model's performance.
|
| 9 |
When both metrics are smaller, it indciates that the model performs better. Our models performance: Overall Mean Squared Error: 0.07532746344804764, Mean Absolute Error: 0.1635677814483642
|
| 10 |
|
| 11 |
-
Please **cite**: "Wang, R., and Sun, K. 2024. Personality Detection
|
| 12 |
|
| 13 |
The project of predicting human cognition and emotoon, and training details are available at: https://github.com/fivehills/detecting_personality
|
| 14 |
|
|
|
|
| 8 |
Due to the fact that the output values are continuous, it is better to use mean squared errors or mean absolute error to evaluate the model's performance.
|
| 9 |
When both metrics are smaller, it indciates that the model performs better. Our models performance: Overall Mean Squared Error: 0.07532746344804764, Mean Absolute Error: 0.1635677814483642
|
| 10 |
|
| 11 |
+
Please **cite**: "Wang, R., and Sun, K. 2024. Personality Detection Models with Continuous Ouput Values Trained by Mixed Strategies" if you use this model.
|
| 12 |
|
| 13 |
The project of predicting human cognition and emotoon, and training details are available at: https://github.com/fivehills/detecting_personality
|
| 14 |
|