Text Moderation Enhanced Edition 2.0 Multilingual PLUS Service - Content Moderation

Text Moderation 2.0 features upgraded multilingual model capabilities. It can automatically identify languages and supports a wider range of languages. It provides moderation policies and a tag system tailored for international business scenarios. This topic describes the features and usage of the Text Moderation 2.0 multilingual service.

Features

Compared with the multilingual moderation service of Text Moderation 1.0, Text Moderation 2.0 uses independent policies and a tag system to meet international business requirements. It also provides more features to simplify business operations and assist with manual review.

Comparison item	Text Moderation 2.0	Text Moderation 1.0
Multilingual capabilities	Supports 38 languages.	Supports 18 languages.
Moderation capabilities	Uses multiple models in parallel. The policies are more precise because they are based on language and region attributes.	Uses a single model. The policies balance accuracy and recall based on language attributes.
Tag system	Uses an internationalized tag system. It adds internationalized tags such as profanity and regional, and supports multiple risk tags and sub-tags.	Uses the tag system for Chinese scenarios and supports only a single risk tag.
Detection scope	You can configure all detection scopes in the console and enable or disable them as needed. The configurations directly map to the detection results.	Supports general detection scopes, which do not directly map to the detection results.
API features	You do not need to specify the input language because the service can automatically identify it. After moderation, the service returns the language type and the translated English content to assist with manual review.	You must specify the input language. The service does not return translated content.

Supported languages

The Text Moderation 2.0 multilingual service supports 38 languages.

Language type	English name	Language code
English	English	en
Simplified Chinese	Chinese	zh
Traditional Chinese	Traditional Chinese	zh-tw
Indonesian	Indonesian	id
Malay	Malay	ms
Thai	Thai	th
Vietnamese	Vietnamese	vi
Tagalog	Tagalog	tl
Hindi	Hindi	hi
Arabic	Arabic	ar
Turkish	Turkish	tr
French	French	fr
German	German	de
Russian	Russian	ru
Portuguese	Portuguese	pt
Spanish	Spanish	es
Italian	Italian	it
Dutch	Dutch	nl
Polish	Polish	pl
Japanese	Japanese	ja
Korean	Korean	ko
Urdu	Urdu	ur
Uighur	Uighur	ug
Bengali	Bengali	bn
Persian	Persian	fa
Swedish	Swedish	sv
Danish	Danish	da
Norwegian	Norwegian	no
Icelandic	Icelandic	is
Finnish	Finnish	fi
Belarusian	Belarusian	be
Lithuanian	Lithuanian	lt
Czech	Czech	cs
Slovak	Slovak	sk
Hungarian	Hungarian	hu
Modern Greek	Modern Greek	el
Romanian	Romanian	ro
Irish	Irish	ga

Internationalized tags

The Text Moderation 2.0 Multilingual PLUS service uses an internationalized tag system. If the content contains multiple types of risks, multiple tags can be returned simultaneously. Tag categories include, but are not limited to, the following:

Label	Confidence score range	Description
pornographic_adult	0 to 100. The higher the score, the higher the confidence level.	Suspected pornographic content
sexual_terms	0 to 100. The higher the score, the higher the confidence level.	Suspected sexual health content
sexual_suggestive	0 to 100. The higher the score, the higher the confidence level.	Suspected vulgar content
sexual_orientation	0 to 100. The higher the score, the higher the confidence level.	Suspected sexual orientation content
regional_cn	0 to 100. The higher the score, the higher the confidence level.	Suspected domestic political content
regional_illegal	0 to 100. The higher the score, the higher the confidence level.	Suspected illegal political content
regional_controversial	0 to 100. The higher the score, the higher the confidence level.	Suspected political controversy
regional_racism	0 to 100. The higher the score, the higher the confidence level.	Suspected racism
violent_extremist	0 to 100. The higher the score, the higher the confidence level.	Suspected extremist organizations
violent_incidents	0 to 100. The higher the score, the higher the confidence level.	Suspected extremist content
violent_weapons	0 to 100. The higher the score, the higher the confidence level.	Suspected weapons and ammunition
violence_unscList	0 to 100. The higher the score, the higher the confidence level.	United Nations Security Council Consolidated List
contraband_drug	0 to 100. The higher the score, the higher the confidence level.	Suspected drug-related content
contraband_gambling	0 to 100. The higher the score, the higher the confidence level.	Suspected gambling-related content
inappropriate_ethics	0 to 100. The higher the score, the higher the confidence level.	Suspected content with undesirable values
inappropriate_profanity	0 to 100. The higher the score, the higher the confidence level.	Suspected abusive or insulting content
inappropriate_oral	0 to 100. The higher the score, the higher the confidence level.	Suspected vulgar oral content
inappropriate_religion	0 to 100. The higher the score, the higher the confidence level.	Suspected religious profanity
pt_to_contact	0 to 100. The higher the score, the higher the confidence level.	Suspected contact information for advertising
pt_to_sites	0 to 100. The higher the score, the higher the confidence level.	Suspected off-site traffic diversion
customized	0 to 100. The higher the score, the higher the confidence level.	Hit a custom keyword library

Billing

The Text Moderation 2.0 service supports the pay-as-you-go billing method.

Pay-as-you-go

Moderation type	Supported business scenario (service)	Unit price
Basic text moderation (text_standard)	Multilingual detection for international business (professional version): comment_multilingual_pro_global	USD 0.3 per 1,000 calls

Integration guide

Step 1: Activate the service

Visit Activate Service to activate the Text Moderation 2.0 service.

After you activate the Text Moderation 2.0 service, the default billing method is pay-as-you-go. You are charged based on your actual usage on a daily basis. If you do not call the service, you are not charged. After you integrate with the API, the system automatically generates bills based on your usage. For more information, see Billing.

Step 2: Grant permissions to a RAM user

Before you integrate with the SDK or API, you must grant permissions to a RAM user. You can create an AccessKey pair for an Alibaba Cloud account or a RAM user. You must use an AccessKey pair to complete identity verification when you call an Alibaba Cloud API. For more information about how to obtain an AccessKey pair, see Obtain an AccessKey pair.

Procedure

Log on to the RAM console as a RAM administrator.
Create a RAM user.

For more information, see Create a RAM user.
Grant the AliyunYundunGreenWebFullAccess system policy to the RAM user.

For more information, see Grant permissions to a RAM user.

After completing the preceding operations, you can call the Content Moderation API as the RAM user.

Step 3: Install and integrate with the SDK

The service is available in the following regions. For more information about the SDK for the Text Moderation 2.0 service, see Integration guide.

Region	Public endpoint	VPC endpoint
Singapore	green-cip.ap-southeast-1.aliyuncs.com	green-cip-vpc.ap-southeast-1.aliyuncs.com
UK (London)	https://green-cip.eu-west-1.aliyuncs.com	Not available
US (Virginia)	https://green-cip.us-east-1.aliyuncs.com	https://green-cip-vpc.us-east-1.aliyuncs.com
US (Silicon Valley)	https://green-cip.us-west-1.aliyuncs.com	Not available
Germany (Frankfurt)	green-cip.eu-central-1.aliyuncs.com	Not available

Note

The configurations for the UK (London) region reuse the console configurations of the Singapore region. The configurations for the US (Silicon Valley) and Germany (Frankfurt) regions reuse the console configurations of the US (Virginia) region.

API

Usage notes

Business interface: TextModerationPlus

You can call this operation to create a text content moderation task. For more information about how to construct an HTTP request, see Request structure. You can also use a sample HTTP request. For more information, see Integration guide.

Billing information:
This is a billable operation. You are charged only for requests that return a 200 HTTP status code. You are not charged for requests that return other error codes. For more information about billing methods, see Billing.

QPS limit

The queries per second (QPS) limit for a single user on this API is 100 calls per second. If you exceed this limit, your API calls are throttled, which may affect your business.

Request parameters

Name	Type	Required	Example	Description
Service	String	Yes	comment_multilingual_pro_global	The type of the moderation service. Valid value: comment_multilingual_pro_global: multilingual detection for international business
ServiceParameters	JSONString	Yes		The parameter set required by the moderation service. It is a JSON string. For more information about each string, see ServiceParameters.

Table 1. ServiceParameters

Name

Type

Required

Example

Description

content

String

Yes

Content to be detected

The text content to be moderated. The text cannot exceed 600 characters in length.

dataId

String

text0424****

The data ID that corresponds to the detection object.

It can consist of uppercase letters, lowercase letters, digits, underscores (_), hyphens (-), and periods (.). The ID cannot exceed 64 characters in length and can be used to uniquely identify your business data.

Response parameters

Name	Type	Example	Description
Code	Integer	200	The status code. For more information, see Code description.
Data	JSONObject		The data of the moderation result. For more information, see Data.
Message	String	OK	The response message for the request.
RequestId	String	AAAAAA-BBBB-CCCCC-DDDD-EEEEEEEE****	The request ID.

Table 2. Data

Name	Type	Example	Description
Result	JSONArray		The results such as the detected risk labels and confidence scores. For more information, see Result.
DataId	String	text0424****	The data ID that corresponds to the detection object. Note If you pass the dataId in the request parameters for detection, the corresponding dataId is returned here.
RiskLevel	String	high	The risk level, which is returned based on the configured high and low risk scores. Valid values: high: high risk (If a custom keyword library is hit, the risk level is high by default.) medium: medium risk low: low risk none: no risk detected Note We recommend that you handle high-risk content directly. We recommend that you manually review medium-risk content. We recommend that you handle low-risk content only when you have high recall requirements. In other cases, we recommend that you handle low-risk content in the same way as content with no risk detected. You can configure risk scores in the Content Moderation console.
TranslatedContent	String	Translated text	The translated text content.
DetectedLanguage	String	en	The detected language.

Table 3. Result

Name	Type	Example	Description
Label	String	political_xxx	The label returned after the text content is moderated. Multiple labels and scores may be detected. For more information about the supported labels, see the Internationalized tags section.
Confidence	Float	81.22	The confidence score, which ranges from 0 to 100 and is accurate to two decimal places. Some labels do not have a confidence score.
Riskwords	String	AA,BB,CC	The detected sensitive words. Multiple words are separated by commas. Some labels do not return sensitive words.
CustomizedHit	JSONArray	[{"LibName":"...","Keywords":"..."}]	When a custom library is hit, the Label is customized, and the name of the custom library and the custom words are returned. For more information, see CustomizedHit.
Description	String	Suspected pornographic content	The description of the Label field. Important This field is an explanation of the Label field. It may be changed or adjusted. We recommend that you handle the Label field for the actual processing result and do not rely on this field for result disposition.

Table 4. CustomizedHit

Name	Type	Example	Description
LibName	String	Custom library 1	The name of the custom library.
Keywords	String	Custom word 1,Custom word 2	The custom words. Multiple words are separated by commas.

Example

Request example

{
    "Service": "comment_detection_pro_global",
    "ServiceParameters": {
        "content": "testing content",
        "dataId": "text0424****"
    }
}

Response example:

Hit a system policy:

{
    "Code": 200,
    "Data": {
        "Result": [
            {
                "Label": "political_entity",
                "Description": "Suspected political entity",
                "Confidence": 100.0,
                "RiskWords": "Word A,Word B,Word C"
            },
            {
                "Label": "political_figure",
                "Description": "Suspected political figure",
                "Confidence": 100.0,
                "RiskWords": "Word A,Word B,Word C"
            }
        ],
        "RiskLevel": "high",
        "DetectedLanguage": "en",
        "TranslatedContent": "Translated text content",
        "DataId": "text0424****"
    },
    "Message": "OK",
    "RequestId": "AAAAAA-BBBB-CCCCC-DDDD-EEEEEEEE****"
}

Hit a custom keyword library:

{
    "Code": 200,
    "Data": {
        "Result": [
            {
                "Description": "Hit a custom library",
                "CustomizedHit": [
                    {
                        "LibName": "Custom library name 1",
                        "KeyWords": "Custom keyword"
                    }
                ],
                "Confidence": 100,
                "Label": "customized"
            }
        ],
        "RiskLevel": "high",
        "DataId": "text0424****"
    },
    "Message": "OK",
    "RequestId": "AAAAAA-BBBB-CCCCC-DDDD-EEEEEEEE****"
}

Code description

Code	Status code	Description
200	OK	The request was successful.
400	BAD_REQUEST	The request is invalid. This may be because the request parameters are incorrect. Check the request parameters carefully.
407	NOT_SUPPORT	The language type cannot be identified or is not supported.
408	PERMISSION_DENY	This may be because your account is not authorized, has an overdue payment, has not been activated, or has been disabled.
500	GENERAL_ERROR	An error occurred. This may be a temporary server-side error. We recommend that you retry. If this error code persists, contact us through online support.
581	TIMEOUT	A timeout occurred. We recommend that you retry. If this error code persists, contact us through online support.
588	EXCEED_QUOTA	The request frequency exceeds the quota.