Text Analytics
A text mining AI service that uncovers insights such as sentiment analysis, entities, relations, and key phrases in unstructured text
Mine insights from text
Mine insights in unstructured text using natural language processing (NLP)—no machine learning expertise required. Gain a deeper understanding of customer opinions with sentiment analysis. Identify key phrases and entities such as people, places, and organizations to understand common topics and trends. Classify medical terminology using domain-specific, pretrained models. Evaluate text in a wide range of languages.
Broad entity extraction
Identify important concepts in text, including key phrases and named entities such as people, events, and organizations.
Powerful sentiment analysis
Examine what customers are saying about your brand and analyze sentiments around specific topics through opinion mining.
Robust language detection
Analyze text input in several languages.
Flexible deployment
Run Text Analytics anywhere—in the cloud, on-premises, or at the edge in containers.
| Languages: | English (confidence: 100 %) |
|---|---|
| Key phrases: | place, online menu, great menu, marvelous food, midtown NYC, week, dinner party, Contoso Steakhouse, pre-order, John Doe, Sirloin steak, chief cook, owner, kitchen, spot, dining, complaint, email |
| Sentiment: |
Document
MIXED
86%
Positive
0%
Neutral
14%
Negative
Sentence 1
POSITIVE
99%
Positive
1%
Neutral
0%
Negative
Sentence 2
POSITIVE
100%
Positive
0%
Neutral
0%
Negative
Sentence 3
POSITIVE
100%
Positive
0%
Neutral
0%
Negative
Sentence 4
POSITIVE
100%
Positive
0%
Neutral
0%
Negative
Sentence 5
POSITIVE
100%
Positive
0%
Neutral
0%
Negative
Sentence 6
NEUTRAL
0%
Positive
100%
Neutral
0%
Negative
Sentence 7
NEGATIVE
0%
Positive
0%
Neutral
100%
Negative
Sentence 8
POSITIVE
100%
Positive
0%
Neutral
0%
Negative
|
| Named Entities: | Contoso [Organization] Steakhouse [Location] NYC [Location-GPE] last week [DateTime-DateRange] dinner party [Event] chief cook [PersonType] owner [PersonType] John Doe [Person] kitchen [Location-Structural] Sirloin steak [Product] www.contososteakhouse.com [URL] 312-555-0176 [Phone Number] email [Skill] order@contososteakhouse.com [Email] contososteakhouse [Organization] |
| PII Entities: |
Type: Organization Value: Contoso Type: DateTime Value: last week Type: PersonType Value: chief cook Type: PersonType Value: owner Type: Person Value: John Doe Type: Phone Number Value: 312-555-0176 Type: Email Value: order@contososteakhouse.com Type: Organization Value: contososteakhouse |
| Linked Entities: | We went to Contoso Steakhouse located at midtown NYC last week for a dinner party, and we adore the spot! They provide marvelous food and they have a great menu. The chief cook happens to be the owner (I think his name is John Doe) and he is super nice, coming out of the kitchen and greeted us all. We enjoyed very much dining in the place! The Sirloin steak I ordered was tender and juicy, and the place was impeccably clean. You can even pre-order from their online menu at www.contososteakhouse.com, call 312-555-0176 or send email to order@contososteakhouse.com! The only complaint I have is the food didn't come fast enough. Overall I highly recommend it! |
{
"languageDetection": {
"documents": [
{
"id": "fb4a0643-2f15-4d14-a0ec-396bd985b802",
"detectedLanguage": {
"name": "English",
"iso6391Name": "en",
"confidenceScore": 0.99
}
}
],
"errors": [],
"modelversion": "2021-01-05"
},
"keyPhrases": {
"documents": [
{
"id": "fb4a0643-2f15-4d14-a0ec-396bd985b802",
"keyPhrases": [
"place",
"online menu",
"great menu",
"marvelous food",
"midtown NYC",
"week",
"dinner party",
"Contoso Steakhouse",
"pre-order",
"John Doe",
"Sirloin steak",
"chief cook",
"owner",
"kitchen",
"spot",
"dining",
"complaint",
"email"
]
}
],
"errors": [],
"modelversion": "2020-07-01"
},
"sentiment": {
"documents": [
{
"id": "fb4a0643-2f15-4d14-a0ec-396bd985b802",
"sentiment": "mixed",
"confidenceScores": {
"positive": 0.86,
"neutral": 0.0,
"negative": 0.14
},
"sentences": [
{
"sentiment": "positive",
"confidenceScores": {
"positive": 0.99,
"neutral": 0.01,
"negative": 0.0
},
"offset": 0,
"length": 105
},
{
"sentiment": "positive",
"confidenceScores": {
"positive": 1.0,
"neutral": 0.0,
"negative": 0.0
},
"offset": 106,
"length": 55
},
{
"sentiment": "positive",
"confidenceScores": {
"positive": 1.0,
"neutral": 0.0,
"negative": 0.0
},
"offset": 162,
"length": 137
},
{
"sentiment": "positive",
"confidenceScores": {
"positive": 1.0,
"neutral": 0.0,
"negative": 0.0
},
"offset": 300,
"length": 41
},
{
"sentiment": "positive",
"confidenceScores": {
"positive": 1.0,
"neutral": 0.0,
"negative": 0.0
},
"offset": 342,
"length": 85
},
{
"sentiment": "neutral",
"confidenceScores": {
"positive": 0.0,
"neutral": 1.0,
"negative": 0.0
},
"offset": 428,
"length": 139
},
{
"sentiment": "negative",
"confidenceScores": {
"positive": 0.0,
"neutral": 0.0,
"negative": 1.0
},
"offset": 568,
"length": 62
},
{
"sentiment": "positive",
"confidenceScores": {
"positive": 1.0,
"neutral": 0.0,
"negative": 0.0
},
"offset": 631,
"length": 30
}
]
}
],
"errors": [],
"modelversion": "2020-04-01"
},
"entities": {
"documents": [
{
"id": "fb4a0643-2f15-4d14-a0ec-396bd985b802",
"entities": [
{
"text": "Contoso",
"category": "Organization",
"subcategory": null,
"offset": 11,
"length": 7,
"confidencescore": 0.58
},
{
"text": "Steakhouse",
"category": "Location",
"subcategory": null,
"offset": 19,
"length": 10,
"confidencescore": 0.61
},
{
"text": "NYC",
"category": "Location",
"subcategory": "GPE",
"offset": 49,
"length": 3,
"confidencescore": 0.82
},
{
"text": "last week",
"category": "DateTime",
"subcategory": "DateRange",
"offset": 53,
"length": 9,
"confidencescore": 0.8
},
{
"text": "dinner party",
"category": "Event",
"subcategory": null,
"offset": 69,
"length": 12,
"confidencescore": 0.81
},
{
"text": "chief cook",
"category": "PersonType",
"subcategory": null,
"offset": 166,
"length": 10,
"confidencescore": 0.63
},
{
"text": "owner",
"category": "PersonType",
"subcategory": null,
"offset": 195,
"length": 5,
"confidencescore": 0.93
},
{
"text": "John Doe",
"category": "Person",
"subcategory": null,
"offset": 222,
"length": 8,
"confidencescore": 0.98
},
{
"text": "kitchen",
"category": "Location",
"subcategory": "Structural",
"offset": 272,
"length": 7,
"confidencescore": 0.75
},
{
"text": "Sirloin steak",
"category": "Product",
"subcategory": null,
"offset": 346,
"length": 13,
"confidencescore": 0.91
},
{
"text": "www.contososteakhouse.com",
"category": "URL",
"subcategory": null,
"offset": 477,
"length": 25,
"confidencescore": 0.8
},
{
"text": "312-555-0176",
"category": "Phone Number",
"subcategory": null,
"offset": 509,
"length": 12,
"confidencescore": 0.8
},
{
"text": "email",
"category": "Skill",
"subcategory": null,
"offset": 530,
"length": 5,
"confidencescore": 0.8
},
{
"text": "order@contososteakhouse.com",
"category": "Email",
"subcategory": null,
"offset": 539,
"length": 27,
"confidencescore": 0.8
},
{
"text": "contososteakhouse",
"category": "Organization",
"subcategory": null,
"offset": 545,
"length": 17,
"confidencescore": 0.45
}
]
}
],
"errors": [],
"modelversion": "2021-01-15"
},
"entityLinking": {
"documents": [
{
"id": "fb4a0643-2f15-4d14-a0ec-396bd985b802",
"entities": [
{
"name": "Steakhouse",
"matches": [
{
"text": "Steakhouse",
"offset": 19,
"length": 10,
"score": 0.0
}
],
"language": "en",
"id": "Steakhouse",
"url": "https://en.wikipedia.org/wiki/Steakhouse",
"datasource": "Wikipedia"
},
{
"name": "New York City",
"matches": [
{
"text": "NYC",
"offset": 49,
"length": 3,
"score": 0.0
}
],
"language": "en",
"id": "New York City",
"url": "https://en.wikipedia.org/wiki/New_York_City",
"datasource": "Wikipedia"
},
{
"name": "John Doe",
"matches": [
{
"text": "John Doe",
"offset": 222,
"length": 8,
"score": 0.0
}
],
"language": "en",
"id": "John Doe",
"url": "https://en.wikipedia.org/wiki/John_Doe",
"datasource": "Wikipedia"
},
{
"name": "Sirloin steak",
"matches": [
{
"text": "Sirloin steak",
"offset": 346,
"length": 13,
"score": 0.0
}
],
"language": "en",
"id": "Sirloin steak",
"url": "https://en.wikipedia.org/wiki/Sirloin_steak",
"datasource": "Wikipedia"
}
]
}
],
"errors": [],
"modelversion": "2020-02-01"
},
"entityPII": {
"documents": [
{
"id": "fb4a0643-2f15-4d14-a0ec-396bd985b802",
"entities": [
{
"text": "Contoso",
"category": "Organization",
"subcategory": null,
"offset": 11,
"length": "7",
"confidencescore": 0.58
},
{
"text": "last week",
"category": "DateTime",
"subcategory": "DateRange",
"offset": 53,
"length": "9",
"confidencescore": 0.8
},
{
"text": "chief cook",
"category": "PersonType",
"subcategory": null,
"offset": 166,
"length": "10",
"confidencescore": 0.63
},
{
"text": "owner",
"category": "PersonType",
"subcategory": null,
"offset": 195,
"length": "5",
"confidencescore": 0.93
},
{
"text": "John Doe",
"category": "Person",
"subcategory": null,
"offset": 222,
"length": "8",
"confidencescore": 0.98
},
{
"text": "312-555-0176",
"category": "Phone Number",
"subcategory": null,
"offset": 509,
"length": "12",
"confidencescore": 0.8
},
{
"text": "order@contososteakhouse.com",
"category": "Email",
"subcategory": null,
"offset": 539,
"length": "27",
"confidencescore": 0.8
},
{
"text": "contososteakhouse",
"category": "Organization",
"subcategory": null,
"offset": 545,
"length": "17",
"confidencescore": 0.45
}
]
}
],
"errors": [],
"modelversion": "2021-01-15"
}
}
Identify and categorize important concepts
Extract a broad range of prebuilt entities such as people, places, organizations, dates/times, numerals, and over 100 types of personally identifiable information (PII), including protected health information (PHI), in documents using named entity recognition.
Extract key phrases in unstructured text
Quickly evaluate and identify the main points in unstructured text. Get a list of relevant phrases that best describe the subject of each record using key phrase extraction. Easily organize information to make sense of important topics and trends.
Better understand customer perception
Analyze positive and negative sentiment in social media, customer reviews, and other sources to get a pulse on your brand. Use opinion mining to explore customers' perception of specific attributes of products or services in text.
Process unstructured medical data
Extract insights from unstructured clinical documents such as doctors' notes, electronic health records, and patient intake forms using the health feature of Text Analytics in preview. Recognize, classify, and determine relationships between medical concepts such as diagnosis, symptoms, and dosage and frequency of medication.
Detect language of your text
Evaluate text input in a wide range of languages, variants, and dialects using the language detection feature.
Deploy anywhere, from the cloud to the edge
Run Text Analytics wherever your data resides. Build applications that are optimized for both robust cloud capabilities and edge locality using containers.
Comprehensive privacy and security
- Your data stays yours. Microsoft doesn’t collect data from the training performed on your text to improve models.
- Choose where Cognitive Services processes your data with containers.
- Backed by Azure infrastructure, Text Analytics offers enterprise-grade security, availability, compliance, and manageability.
Get the power, control, and customization you need with flexible pricing
- Pay only for what you use, with no upfront costs.
- With Text Analytics, you pay as you go based on the number of transactions.
Text Analytics resources and documentation
Get started with learning resources
Explore popular developer resources
Trusted by companies of all sizes
KPMG streamlines fraud analytics
KPMG is helping financial institutions save millions in compliance costs with its Customer Risk Analytics solution, which uses Text Analytics to detect patterns and keywords to flag compliance risks.
Wilson Allen unlocks insights from unstructured data
Wilson Allen created a powerful AI solution that can help law and professional services firms around the world find unprecedented levels of insight in previously siloed and unstructured data.
IHC empowers service engineers
Royal IHC uses Azure Cognitive Search and Text Analytics to relieve its engineers from time-consuming manual data searches across disparate sources and give them insights on their structured and unstructured data.
LaLiga boosts fan engagement
LaLiga is engaging hundreds of millions of fans around the world with a personal digital assistant, using Text Analytics to process incoming queries and determine user intents in multiple languages.
TIBCO brings root cause analysis to the edge
TIBCO is using Text Analytics and Anomaly Detector to detect and analyze anomalies—sudden changes in data patterns, discover root causes, and provides suggested actions.
Kotak Mahindra Bank accelerates productivity
Kotak Asset Management is transforming customer service management by enabling chatbots to easily analyze subject line, customer information, and email content to identify sentiment and trigger the next best action.
Frequently asked questions about Text Analytics
-
Text Analytics detects a wide range of languages, variants, and dialects. See the language support documentation for more information.
-
Yes. Sentiment analysis and key phrase extraction are available for a select number of languages, and you may request additional languages in the Text Analytics Forum.
-
Key phrase extraction eliminates non-essential words and standalone adjectives. Adjective-noun combinations, such as "spectacular views" or "foggy weather," are returned together. Generally, output consists of nouns and objects of the sentence and is listed in order of importance. Importance is measured by the number of times a particular concept is mentioned, or the relation of that element to other elements in the text.
-
Improvements to models and algorithms are announced if the change is major, and added to the service if the update is minor. Over time, you might find that the same text input results in a different sentiment score or key phrase output. This is a normal and intentional consequence of using managed machine learning resources in the cloud.
-
Yes, now you can use the analyze operation in Preview to combine more than one Text Analytics feature in the same asynchronous call. The analyze operation is currently only available in the Standard (S) pricing tier and follows the same pricing criteria of the S tier.
-
Yes, these services are related: