Research Article
Prediction of Suspect Activity Trajectory in Food Safety Area Based on Multiple U-Model Algorithm
Table 1
Detection result of criminals from social data.
| No. | Specific content | Model outputs | Sentiment score | Crime types |
| 1 | That is going too far! | | | | I’m going to kill these officials and join ISIS. | Negative | −4.9644 | Politics | 2 | It’s a beautiful day today. | Positive | 0.2397 | None | ⋮ | ⋮ | ⋮ | ⋮ | ⋮ | 812 | Terrible! I must destroy this activity. | Negative | −3.8753 | Crime involving guns and explosives | Tomorrow you buy some nitroglycerin. | 813 | He is always bullying me! | Negative | −1.9564 | Food safety and terrorism | I am going to fight back and put sleeping pills in his water. | 814 | The sun is new every day and our life are full of hope. | Positive | 0.8674 | None |
|
|