AnalyzeEntitiesWithSentiment Processor
Part of the GCP Natural Language processor family
This processor takes in an input string and returns textual references to real world items (such as names, places, etcetera). This processor has an added feature compared to the "standard" AnalyzeEntities processor, which is that each entity will also have a sentiment attached to it. This sentiment represents how that particular entity is spoken about (positively or negatively) in the text.
The resulting Sentiments are reported with two values: score and magnitude. Per the official documentation:
scoreranges from -1.0 (negative sentiment) to 1.0 (positive sentiment)magnitudeindicates the overall strength of the emotion (both positive and negative)
This means that, for example, a sentence with a sentiment that has a score of 0.8 and a magnitude of 1.7 means it's a very strongly positive message. Similarly, a sentiment with a score of -0.2 with a magnitude of 0.2 is likely a "lightly" negative message.
Properties
This processor does not have any unique properties outside of the common ones.
Data Output
Field Name
Data Type
Description
entities
array of Entity
The list of entities found by the API
language
string
The language code of the language the input string is in
Entity
EntityField Name
Data Type
Description
mentions
array of Mention
The words/tokens that relate to this entity
sentiment
Sentiment
The sentiment of this entity within the text
Mention
MentionField Name
Data Type
Description
text
string
The raw text of the mention
beginOffset
int
The numer of characters from the beginning of the input string to the beginning of the text of this mention
type
string (EntityType)
The type of mention this is. They follow the same names and descriptions as EntityTypes.
Sentiment
SentimentField Name
Data Type
Description
score
float
A number ranging from -1.0 (negative sentiment) to 1.0 (positive sentiment)
magnitude
float
A number ranging from 0 to +inf representing the absolute magnitude of the sentiment (regardless of score). This number can be thought of as the strength of the emotion (e.g., something being very positive, or slightly negative)
{
"output":{
"entities":[
{
"metadata":{
"wikipedia_url":"https:\/\/en.wikipedia.org\/wiki\/James_Adams_(entrepreneur)",
"mid":"\/m\/0136zb57"
},
"mentions":[
{
"sentiment":{
"score":0.9,
"magnitude":0.9
},
"text":"James Adams",
"type":"PROPER",
"beginOffset":-1
},
{
"sentiment":{
"score":0.9,
"magnitude":0.9
},
"text":"developer",
"type":"COMMON",
"beginOffset":-1
}
],
"type":"PERSON"
},
{
"metadata":{
},
"mentions":[
{
"sentiment":{
"score":0.0,
"magnitude":0.0
},
"text":"scene",
"type":"COMMON",
"beginOffset":-1
}
],
"type":"LOCATION"
},
{
"metadata":{
},
"mentions":[
{
"sentiment":{
"score":0.9,
"magnitude":0.9
},
"text":"attitude",
"type":"COMMON",
"beginOffset":-1
}
],
"type":"OTHER"
},
{
"metadata":{
},
"mentions":[
{
"sentiment":{
"score":0.9,
"magnitude":0.9
},
"text":"work ethic",
"type":"COMMON",
"beginOffset":-1
}
],
"type":"OTHER"
},
{
"metadata":{
},
"mentions":[
{
"sentiment":{
"score":0.0,
"magnitude":0.0
},
"text":"company",
"type":"COMMON",
"beginOffset":-1
}
],
"type":"ORGANIZATION"
},
{
"metadata":{
},
"mentions":[
{
"sentiment":{
"score":0.5,
"magnitude":0.5
},
"text":"character",
"type":"COMMON",
"beginOffset":-1
}
],
"type":"PERSON"
}
],
"language":"en"
},
"raw-input":"James Adams is a fantastic developer who has been on the scene for over ten years. His excellent attitude and steady work ethic contribute to his character. May he stay with our company for many years to come."
}Last updated
Was this helpful?