updated 4 months ago
Google NL is an NLP API to several models for different tasks like sentiment analysis and text classification. Now, you can integrate Google NLP to Stackby to pull in information about people, places, and events, and better understand social media sentiment and customer conversations.
Let's see how you can integrate Google NLP to Stackby.
In this article, we will cover the following:
Why to Integrate Google NLP?
Google's Natural Language API uses powerful machine learning to reveal the structure and meaning of text. You can extract information about people, places, and events, and better understand social media sentiment and customer conversations.
You can use Google NL API to analyze text to detect sentiment, entity, extract entity sentiment, classify content, syntax analysis and many more.
How to Integrate Google NLP?
It is very easy to integrate Google NLP to Stackby.
Step 1: Sign up or login to your Google Developers Console and click on the side navigation bar
Step 2: In the API services Library, search Cloud Natural Language API → Enable API
Once your API is enabled, go back to your account on Stackby (to integrate your workspace) → Workspace settings → API configuration in Stackby and add a new integration for Google NL and paste your API key and save.
Now that you have set up the integration, here is how you can analyze your text:
- Create a stack in the Workspace or go to the stack, and keep the first column or any column as the reference (here it will be the String).
- In the second column, connect to the Google NLP API and rename the column, select "API" as the column property and choose Google NLP as the API and within that Select a Service and then Select the reference column as required. There, you have now integrated your API with a column.
- Add in the string in the first/primary column, click on the refresh arrow and the API will work on the stack. The data will start filling in the consecutive columns (decide which data you want to access by selecting it from our data explorer). Make sure you change the column names and property beforehand; repeat with other columns.
Available API Functions
Analyze Sentiment Understand the overall opinion, feeling or attitude sentiment that is expressed in a block of text Reference Input column: String/Text Output: Sentiment of text Analyze Entities Identify entities within documents, including receipt, invoices and contracts. Label them by types such as date, person, contact information, organization, location, events, products and media Reference Input column: String/Text Output: Type of entities or documents within the text Analyze Syntax Extract tokens and sentences, identify parts of speech and create dependency parse trees of each sentence Reference Input column: String/Text Output: Syntax of the text Analyze Entity Sentiment Understand the overall opinion, feeling or attitude expressed in a block of text that is tuned in to your own domain specific sentiment scores. Reference Input column: String/Text Output: Syntax of the text Classify Text Classify text/documents in more than 700 predefined categories Reference Input column: String/Text Output: Sentimental analysis of the text
The current usage quotas for AutoML Natural Language are 600 prediction requests per minute per project and 600 non-prediction requests per minute per project. These quotas apply collectively to all deployed models.
IMPORTANT NOTE: Google NL is a paid service. There is a free version available, but you still need to have a credit card to use the free service.