Unlock instant, AI-driven research and patent intelligence for your innovation.

A Chinese Microblog Preference Retrieval Method Based on Graph Model

A tendency, graph model technology, applied in the direction of unstructured text data retrieval, special data processing applications, instruments, etc., can solve the problems of information demand deviation, affect retrieval results, and not fully consider context information, etc., to achieve broad application prospects , wide application range and fast retrieval speed

Active Publication Date: 2017-08-11
FUZHOU UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Compared with the two-stage model, this method has the advantages of easy interpretation in theory and more direct and effective expression of information requirements. However, this method may not fully consider the rich context information in microblogs, resulting in deviations in the final information requirements and affecting final search results

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
  • A Chinese Microblog Preference Retrieval Method Based on Graph Model
  • A Chinese Microblog Preference Retrieval Method Based on Graph Model
  • A Chinese Microblog Preference Retrieval Method Based on Graph Model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029]The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0030] The present invention is based on the graph model Chinese micro-blog tendency retrieval method, such as figure 1 shown, including the following steps:

[0031] (1) Preprocess microblogs, including noise removal, word segmentation, and stop word processing, to obtain preprocessed microblogs.

[0032] Because there are some correlation and tendency analysis information in Weibo, including web page links, emoticons, punctuation and stop words, they need to be deleted to ensure the accuracy of subsequent calculation and analysis steps. The denoising process is to remove the following content in the microblog:

[0033] a) Web link, "http: / / t.cn / "; b) Special characters, including "★", "▲", "¥", "『", "◆", "●", "①", etc. ;c) promotion-related characters, including "shared from", "participated in voting", "activity recommendation", ...

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 a Chinese microblog tendency retrieving method based on a graph model. The method comprises the following steps: (1) preprocessing microblogs, including denoising, work segmentation and stop word processing, to obtain preprocessed microblogs; (2) calculating the tendency weight of each tendency word in a tendency dictionary based on a graph model method according to a pre-collected and preprocessed tendency microblog set, and reflecting different tendency intensities of each tendency word; (3) calculating the relevance score of each microblog according to the microblogs and a given query subject, calculating the tendency scores of the microblogs to obtain the tendency score of each microblog, and ranking the microblogs by taking a product of the relevance score and the tendency score of each microblog as the final ranking score of each microblog to obtain a final microblog list. The method has the advantages of high retrieving speed, high accuracy, wide application range and high applicability.

Description

technical field [0001] The present invention relates to the technical field of viewpoint mining and tendency analysis, more specifically, relates to a graph model-based Chinese microblog tendency retrieval method, which can be applied to market research, voting prediction, advertisement analysis, network viewpoint mining, etc., and is applicable to Chinese microblogs, including Sina Weibo, Tencent Weibo, Netease Weibo, etc. Background technique [0002] The tendency retrieval of Weibo aims at retrieving the opinions and opinions of the public on hot topics on microblogs. It is required that the retrieved documents must not only be related to the given query topic, but also have subjective comments on the given query topic. Therefore, it is an effective means to understand people's real views and opinions on various entities such as hot topics and organizations, and it can be applied to projects such as market research, vote prediction, advertising analysis, and network opini...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06F17/30
CPCG06F16/36
Inventor 陈国龙廖祥文陈胡
Owner FUZHOU UNIV