Product feature clustering method based on adjacent word similarity

A clustering method and word similarity technology, applied in the field of comment analysis, can solve time-consuming and other problems

Active Publication Date: 2021-03-26
芜湖汽车前瞻技术研究院有限公司 +1
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, product features are co...

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Product feature clustering method based on adjacent word similarity
  • Product feature clustering method based on adjacent word similarity
  • Product feature clustering method based on adjacent word similarity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The specific implementation manner of the present invention will be described in further detail below by describing the best embodiment with reference to the accompanying drawings.

[0031] The present invention first collects and preprocesses related product review data, then extracts product features, measures the similarity between product features based on the similarity of adjacent words, and finally performs product feature based on the similarity between product features. Clustering, such as figure 1 shown.

[0032] Step 1. Data collection and preprocessing.

[0033] First, write a crawler algorithm to crawl product review data from product forums and professional websites; then, filter spam comments and delete them according to some keywords such as "sofa", "http" and other words; finally, use word segmentation tools to analyze the comment text Word segmentation and part-of-speech tagging, and manually import domain-specific vocabulary dictionaries to improve ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to the technical field of comment analysis, and provides a product feature clustering method based on adjacent word similarity, which comprises the following steps: S1, extracting product features based on product comments, and putting the product features into a product feature set; s2, calculating the similarity of two product features in the product feature set to form a similarity matrix; and S3, clustering the product features by using a hierarchical clustering method to form a tree-shaped product feature clustering structure. A product feature similarity measurementmethod of adjacent word similarity is adopted, and clustering is performed based on the layering of product features so as to better summarize customer comments.

Description

technical field [0001] The invention relates to the technical field of comment analysis, and provides a product feature clustering method based on the similarity of adjacent words. Background technique [0002] In sentiment analysis of product reviews, an important issue is how to generate opinion summaries based on product features. However, due to the limitations of expression habits and limited knowledge, people often use different words and phrases to describe the same product features. For example, in the sentences "The appearance of this car is really beautiful!" and "The most important thing is the appearance." The word "appearance" and the word "appearance" are different product characteristics, but they both express the need for Evaluation of product feature "appearance", in order to better summarize customer opinions, we need to cluster these words and phrases into the same product feature category. Currently, product features are collected manually, which takes ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F16/9535G06F40/247G06F40/289G06K9/62
CPCG06F16/9535G06F40/247G06F40/289G06F18/23G06F18/22
Inventor 王磊赛影辉王志超叶德英肖飞韦圣兵秦玉林
Owner 芜湖汽车前瞻技术研究院有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products