Let's take a closer look at the actual APIs Google offers to make sense of your unstructured data. We know that in a typical business scenario, a company ends up using data that is being generated from multiple sources. Typical examples of widely-used data are relational databases, inventory systems, ERP systems like SAP, and spreadsheets. These data sources use strict data formatting rules and host data accordingly. Hence, the data is known as structured data. Apart from these, a lot of data is generated from a variety of other sources in the form of e-mail, audio, video, images, texts, social media likes, and comments. All these types of data are typically free from strict formatting and hence known as unstructured data. As a business, a prominent and important question is how to process unstructured data which typically constitute nearly 90 percent of a business's data. Unstructured data has tremendous potential to provide detailed insights which can benefit the business. In this section, we will see which AI technologies can be used to process this unstructured data to have business impact. In this module, we're going to concentrate on the Cloud Natural Language API for processing unstructured data in the form of texts. However, keep in mind that there are equivalent APIs for image, video, and audio data. Again, when we say that we're enriching unstructured data, we're saying that we're applying labels to us. We're providing labels for questions like, what is the subject of this e-mail, and does this comment of positive or negative sentiment? The Cloud Natural Language API provides many features with which text analytics can be performed. The first feature is syntactic analysis. Syntactic analysis first breaks up text into a series of tokens, which are generally words and sentences, and provides information about the token's internal structure and its role in the sentence. It can label a token as a noun or verb, singular or plural, first person, or second person, masculine, feminine, or gender neutral, and provides grammatical information such as case, tense, mood, and voice. At the time of this writing, the Cloud Natural Language API supports 10 languages. See online documentation for current language support. The Natural Language API also offers entity analysis for recognizing people, locations, organizations, events, artwork, consumer products, phone numbers, addresses, dates, and numbers. Sentiment analysis identifies the emotional opinion of a writer's attitude. It's presented as a numerical score and a magnitude for the intensity of the feeling. It does not identify specific emotions but groups them into generally positive or negative or neutral. Sad and angry are both negative and funny and happy are both positive. Because these are continuous values, you should define your own thresholds that work for your application, for example, maybe below 10 percent magnitude is not as strong enough feeling or between minus 1.0 and plus 1.0 does not clearly express an emotion. Entity sentiment analysis combines both entity analysis and sentiment analysis and attempts to determine the sentiment, positive or negative expressed about entities within the text. Entity sentiment is represented by numerical score and magnitude values and is determined for each mention of an entity. Those scores are then aggregated into an overall sentiment score and magnitude for an entity. At the time of this writing, content can be classified into 620 categories.
