The output contains information about the status of the request and it divides the text into fragments indicating the reputation associated to the different relevant entities (in this case, organizations and people) detected in each fragment. To do that, it will indicate in which category (or categories) or dimmension/s the fragment is classified according a reputation model for business — that is, which categories affect the reputation of the set of detected entities — and the sentiment associated to each entity in those categories. Information about irony and subjectivity is obtained too.
The information provided is the same for the different output formats and the naming convention used for all fields is lowercase_separated_by_underscore.
{
"status": {
"code": "0",
"msg": "OK",
"credits": "0"
},
"fragment_list": [
{
"text": "Apple lanza el 'mayor adelanto' en la historia del iPhone: http://bit.ly/1tHYVgY",
"inip": "0",
"endp": "79",
"info_list": [
{
"entity": "Apple",
"type": "Top>Organization>Company>TechnologyCompany",
"category": "Innovación y flexibilidad - Innovación",
"relevance": "100",
"sentiment": "P+",
"subjectivity": "OBJECTIVE",
"irony": "NONIRONIC"
}
]
}
],
"category_list": [
{
"category": "Innovación y flexibilidad - Innovación"
}
],
"entity_list": [
{
"entity": "Apple",
"type": "Top>Organization>Company>TechnologyCompany"
}
]
}
Name | Description |
---|---|
status | Describes the request outcome in terms of success or failure. |
status .code | Numerical value of result code. Refer to the error code catalog. |
status .msg | Human-readable error code, if any, orOK . |
status .credits | Credits consumed by the request. |
status .remaining_credits | Credits left to reach the usage limit. |
fragment_list | List of fragments in which the text is divided. Each fragment is represented by an element fragment. |
fragment_list[] .inip | Initial position of the fragment, starting from 0. |
fragment_list[] .endp | End position of the fragment. |
fragment_list[] .info_list | Detailed information from the fragment listed by entity and category. Each piece of information contains the following fields: |
fragment_list[].info_list .entity | Main form of the entity. |
fragment_list[].info_list .type | Type classification hierarchy of the entity. |
fragment_list[].info_list .category | Main form of the category in which the input text is classified. |
fragment_list[].info_list .relevance | Relative relevance value of the category, represented by a number in the 0-100% range, and computed with respect to the top ranked result. |
fragment_list[].info_list .sentiment | This value will provide the sentiment analysis associated to the Possible values for this field are the following tags:
|
fragment_list[].info_list .subjectivity | This field marks the subjectivity of the fragment it refers to. It has two possible values:
|
fragment_list[].info_list .irony | This field indicates the irony of the fragment it refers to. It has two possible values:
|
category_list | List of categories in which the input text is classified. Each category contains the a field |
entity_list | List of entities of type organization or person, identified in the text. Each one will be represented by an element |
entity_list[] .entity | Main form of the entity. |
entity_list[] .type | Type classification hierarchy of the entity. |