Paper innovation measuring method based on SAO-ADV structure

A SAO-ADV and paper technology, applied in the algorithm field of information science and computer technology, can solve the problems that cannot directly reflect the innovation degree of the paper content, and achieve the effect of comprehensive evaluation results

Pending Publication Date: 2020-08-28
SUN YAT SEN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a method for measuring the innovation of papers based on the SAO-ADV structure in order to overcome the technical defects that the existing paper innovation degree evaluation method cannot directly reflect the content of the paper or can only evaluate the innovation degree of the part of the paper

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
  • Paper innovation measuring method based on SAO-ADV structure
  • Paper innovation measuring method based on SAO-ADV structure
  • Paper innovation measuring method based on SAO-ADV structure

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] Such as figure 1 As shown, the innovative measurement method based on the SAO-ADV structure includes the following steps:

[0030] S1: According to the paper and subject / topic to be evaluated, select and screen all the literature of the subject / topic on the data source platform to obtain the background database of the papers to be evaluated and compared;

[0031] S2: Remove the introductory or introductory sentences in the paper background database and the papers to be evaluated, perform word segmentation and part-of-speech tagging on the remaining texts, and perform syntactic analysis on the resulting features of the sentences, and extract the paper background database and the papers to be evaluated SAO-ADV structure;

[0032] S3: Build a Word2Vec semantic similarity model;

[0033] S4: Use the semantic similarity model to calculate the innovation degree of each internal phrase that constitutes the SAO-ADV structure, so as to obtain the SAO-ADV structure and the inno...

Embodiment 2

[0059] More specifically, in order to verify the effectiveness of the innovation measurement model based on the content analysis of academic papers proposed in this study, the only journal named Scientometrics in the field of scientometrics is selected for analysis. Since the journal was founded in 1978, the quality and level of academic papers published have been continuously improved, and it has become an important exchange position for the latest academic achievements in the international scientometrics community. The innovation of published academic papers has been widely reviewed by peers in the scientometrics community. .

[0060] Data acquisition and processing: On the Web of Science database platform, searched with the search formula "SO="Scientometrics" AND PY=2019", and obtained a total of 223 documents (as of September 3, 2019), except that the document type was There were 19 papers in "Letter" and 4 papers in "Correction". Considering the negative impact of short a...

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 provides a method for measuring paper innovation based on an SAO-ADV structure. The method comprises the following steps: constructing a paper background library to be evaluated and compared; removing the paper background library and the sentences with the assertion or introduction property in the to-be-evaluated paper, performing word segmentation processing on the remaining text, performing part-of-speech tagging and syntactic analysis, and extracting SAO-ADV structures of the paper background library and the to-be-evaluated paper; constructing a Word2Vec semantic similarity model; and calculating the innovation degree of each internal phrase forming the SAO-ADV structure by adopting a semantic similarity model to obtain the innovation degree of the SAO-ADV structure and the innovation degree of the to-be-evaluated paper, and completing the measurement of the innovation of the paper. According to the SAO-ADV structure-based paper innovation measurement method provided by the invention, the improved SAO-ADV model is adopted to completely extract the paper content, and the subject terms of the paper are completely connected in series by using the grammatical structure, so that the evaluation result is more comprehensive; meanwhile, the semantic similarity model is utilized, the paper content can be directly evaluated without the help of external metering indexes such as citations, and the quality of the paper content can be better reflected.

Description

technical field [0001] The present invention relates to the field of algorithm technology of information science and computer technology, and more specifically, relates to a method for measuring the innovativeness of papers based on the SAO-ADV structure. Background technique [0002] The innovation of the paper means that in the relevant academic field, the paper puts forward new theories, new methods, new research objects, or carries out relatively perfect development on the basis of existing research. At present, the evaluation method of the innovation degree of academic papers mainly includes two aspects, one is to analyze the objective indicators (citation indicators, social media indicators, etc.) Subjective judgment (such as peer review, etc.). [0003] The evaluation based on objective indicators is mainly based on the objective data after the publication of academic papers to evaluate them. At present, evaluation methods based on objective indicators are mainly di...

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): G06F40/211G06F40/289G06F40/30G06F40/253
CPCG06F40/211G06F40/289G06F40/30G06F40/253
Inventor 侯剑华王东毅
Owner SUN YAT SEN UNIV
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