Research Article
Uncovering Cybercrimes in Social Media through Natural Language Processing
Table 7
Sentiment analysis results for Scenario 2 using SLP Algorithm versus Vader model.
| Sentiment analysis algorithm | Cluster | Polarity | Subjectivity (mean) | Number of tweets | Number of accounts | Negative (%) | Neutral (%) | Positive (%) |
| SLP algorithm (TextBlob library) | 1 | 13.4 | 65.8 | 20.7 | 0.19 | 82 | 81 | 2 | 39.7 | 12.8 | 47.4 | 0.42 | 506 | 452 | 3 | 32.9 | 21.4 | 45.6 | 0.37 | 410 | 355 | 4 | 27.2 | 46.8 | 25.8 | 0.28 | 209 | 201 |
| Vader model (VaderSentiment library) | 1 | 20.7 | 52.4 | 26.8 | — | 82 | 81 | 2 | 55.1 | 4.9 | 39.9 | — | 506 | 452 | 3 | 41.7 | 14.6 | 43.6 | — | 410 | 355 | 4 | 29.1 | 38.7 | 32.0 | — | 209 | 201 |
|
|