Tweet Sentiment Node
Sentiment Analysis,
SemEval 2017 - Sentiment Analysis in Twitter (Rosenthal et al., 2019) - 3 labels: positive, neutral, negative
Input
- payload string
- Tweet text (from twitter sensor)
Example message:
{
"payload": "@andst7 Important. South Korea is currently tracking to lose about half its population roughly every generation. Long lifespa…"
}Output
This node constitutes of multiple outputs which automatically get routed to the correct output based on classification.
| Output | Type |
|---|---|
| 1 | Positive |
| 2 | Neutral |
| 3 | Negative |
The message will be enriched by the sentiment property:
- payload string
- Original tweet text
- sentiment.positive float
- Positive indicator; range=
0.0-1.0 - sentiment.neutral float
- Neutral indicator; range=
0.0-1.0 - sentiment.negative float
- Negative indicator; range=
0.0-1.0
Example message:
{
"payload": "@andst7 Important. South Korea is currently tracking to lose about half its population roughly every generation. Long lifespa…",
"sentiment": {
"negative": 0.5797,
"neutral": 0.396,
"positive": 0.0243
}
}Note, these values sum up to 1.0.
Configuration
- Name optional
- unique name for this node
- Enable Filter flag
- Whether to enable threshold-based filtering
- Positive Threshold float [0.0-1.0]
- Specify the minimum required positive value
- Neutral Threshold float [0.0-1.0]
- Specify the minimum required neutral value
- Negative Threshold float [0.0-1.0]
- Specify the minimum required negative value
Higher values in thresholds can be used to increase certainty.
Last updated on
Sep 15, 2022