Guide
Analyze

Generate Sentiments Indicators

Generate Sentiments Indicators

Emotion indicators have been deprecated and are no longer available through the TextReveal® API

Using the Named Entity Recognition (NER)

Steps

workertasks
quality-scoreFilters out document not reaching a predefined threshold.
ner-linkingFilters out document not mentioning any of the companies defined in the request.
embedder-indicatorGenerates indicators for each sentence composing the document.

Some workers are restricted to certain languages, see the Language Support page for more informations

Query

POST /analyze/dataset

payload.json
{
  "workers": ["quality-score", "ner-linking", "embedder-indicators"],
  "start_date": "2019-01-31",
  "qscore": 50,
  "entities": [
    {
      "context": "Apple is a multinational corporation that designs, manufactures, and markets consumer electronics, personal computers, and software.",
      "entity_of_interest": "Q312",
      "keywords": ["Tim Cook", "Apple TV"]
    },
    {
      "context": "Boeing Company manufactures and sells aircraft, rotorcraft, rockets, and satellites and provides product leasing and support services.",
      "entity_of_interest": "Q66",
      "keywords": ["Boeing", "Alteon Training"]
    }
  ],
  "end_date": "2019-02-01"
}

Using the NER and the entity-similarity

Steps

workertasks
quality-scoreFilters out document not reaching a predefined threshold.
ner-linkingFilters out document not mentioning any of the companies defined in the request.
entity-similarityCalculates the cosine similarity between the each entity description and each sentence where the entity is detected.
Filters out document not reaching a given similarity threshold.
embedder-indicatorGenerates indicators for each sentence composing the document.

Query

POST /analyze/dataset

payload.json
{
  "workers": ["quality-score", "ner-linking", "entity-similarity", "embedder-indicators"],
  "start_date": "2019-01-31",
  "qscore": 50,
  "entities": [
    {
      "context": "Apple is a multinational corporation that designs, manufactures, and markets consumer electronics, personal computers, and software.",
      "entity_of_interest": "Q312",
      "keywords": ["Tim Cook", "Apple TV"]
    },
    {
      "context": "Boeing Company manufactures and sells aircraft, rotorcraft, rockets, and satellites and provides product leasing and support services.",
      "entity_of_interest": "Q66",
      "keywords": ["Boeing", "Alteon Training"]
    }
  ],
  "end_date": "2019-02-01"
}

Using the raw-matcher and the entity-similarity

Steps

workertasks
quality-scoreFilters out document not reaching a predefined threshold.
raw-matcherAnnotates the mentions of entities keywords within the sentences.
entity-similarityCalculates the cosine similarity between the each entity description and each sentence where the entity is detected.
Filters out document not reaching a given similarity threshold.
embedder-indicatorGenerates indicators for each sentence composing the document.

Query

POST /analyze/dataset

payload.json
{
  "workers": ["quality-score", "raw-matcher", "entity-similarity", "embedder-indicators"],
  "start_date": "2019-01-31",
  "qscore": 50,
  "entities": [
    {
      "context": "Apple is a multinational corporation that designs, manufactures, and markets consumer electronics, personal computers, and software.",
      "entity_of_interest": "Q312",
      "keywords": ["Tim Cook", "Apple TV"]
    },
    {
      "context": "Boeing Company manufactures and sells aircraft, rotorcraft, rockets, and satellites and provides product leasing and support services.",
      "entity_of_interest": "Q66",
      "keywords": ["Boeing", "Alteon Training"]
    }
  ],
  "end_date": "2019-02-01"
}