Customer Review Analysis API Reference

Customer Review Analysis

GET/POST /ai/review/analysis

Customer Review Analysis is a multi-dimensional qualitative in-depth analysis of customer reviews. It can analyze the product freatures and emotional information described by customer reviews. Combined with statistical data processing, it can help merchants accurately grasp customer insights and market trends to improve product quality and customer satisfaction.

Request Parameters

Parameter
Type
Required
Description

single_review

string

Yes

The reviews need to be analyzed.

Sample: I am very satisfied with this purchase. The logistics service is really great!

file_type

string

Yes

The file type input and only single text reviews are supported now

Sample: single_review

source_language

string

Yes

The source language. Only English is supported now.

Sample: en

cate

string

Yes

The aspect of analysis such as logistics and seller service. You can input multiple aspects you want to analyze. Please refer to the appendix of the capability description document for the specific aspects supported.

Sample: logistics,seller service

scene

string

No

Analysis scenes

Sample: ABSA

Sample Request

{
  "single_review": "I am very satisfied with this purchase. The logistics service is really great!", 
  "file_type": "single_review",
  "source_language": "en", 
  "scene": "ABSA", 
  "cate": "logistics,seller service" 
}

Response Parameters

Parameter
Type
Description

resCode

Number

The returned result code, where 200 indicates success. For detailed error codes, please refer to the error code list.

data

Object

The returned request information.

data.usage

Number

The number of result.

data.analysis

Arrray

The result of analysis.

requestId

String

A unique task ID. It is used for subsequent result query requests.

success

Boolean

The status of the returned request, indicating whether the request was successful.

resMessage

String

Error message,"content has sensitive data, please try other input".

Sample Response

{
    "seller service": [], 
    "logistics": [["logistics", "delivery", "great", "fast"]] 
}

Errors

Error Code
Error Message
Description

500

system error

System error.

501

rate limit exceed

The current interface has reached the current limit. Please contact us via navigation bar or email us (aidge_support@service.alibaba.com) to increase the current limit value.

700

invalid input

The format of the input parameters does not meet the requirements, and resMessage will return detailed fields that do not meet the requirements.

801

model failed

Internal call exception, please contact us via navigation bar or email us (aidge_support@service.alibaba.com) for troubleshooting.

1000

content has sensitive data, please try other input

Content has sensitive data and cannot be handled now. Please try other input.

1001

content control failed, please retry

Content risk failed, please try other input. If an error persists,please contact us via navigation bar or email us (aidge_support@service.alibaba.com) for troubleshooting.

1002

content risk filter failed, please contact us

Content risk failed, please contact us via navigation bar or email us (aidge_support@service.alibaba.com).

1007

text language is not supported

The input language is not supported,please input correct language.

1100

The input text length is too long

The input text length is too long(maximum is 4096 words),please adjust the length.

Last updated