Keyword Extraction
Zia Keyword Extraction is a part of Text Analytics that processes textual content and extracts the highlights of the text. The extracted terms are grouped into two categories: Keywords and Keyphrases. These highlights deliver a concise summary of the text and provide an abstraction of the whole text.
Keyword Extraction is a highly useful feature if you want to skim through long textual content and just obtain the essential information and action items from it. You will be able to identify the subject matter and the gist of the text easily from the response, and save valuable time.
Execute Keyword Extraction
Description
You can use this API to perform Keyword Extraction on a block of text of upto 1500 characters in a single request. You can pass the text in the JSON body of the request, as shown in the sample request.
Request Details
Request URL
{api-domain}/baas/v1/project/{project_id}/ml/text-analytics/keyword-extraction
Request Headers
Authorization: Zoho-oauthtoken {oauth_token}
content-type: application/json
Optional Headers
CATALYST-ORG: {org_id}
Environment: Development
Scope
ZohoCatalyst.mlkit.READ
Request JSON Properties
Response Details
The response contains an array of the key words, and another array of the key phrases that are extracted from the text.
curl -X POST
https://api.catalyst.zoho.com/baas/v1/project/4000000006007/ml/text-analytics/keyword-extraction
-H “Authorization: Zoho-oauthtoken 1000.910*************************16.2f*************************57”
-H “Content-Type: application/json”
-d ‘{
“document”:
“[Catalyst is a full-stack cloud-based serverless development tool, that provides backend functionalities to build applications and microservices on various platforms.]”
}’
{
"status": "success",
"data": [
{
"keyword_extractor": {
"keywords": [
"microservices",
"applications"
],
"keyphrases": [
"backend functionalities",
"various platforms"
]
}
},
{
"keyword_extractor": {
"keywords": [
"Catalyst"
],
"keyphrases": [
"cloud-based serverless development tool"
]
}
}
]
}
Yes
No
Send your feedback to us