Answerer recommendation method for community question and answer platform
A community question answering and recommendation method technology, applied in the recommendation field, can solve problems such as less user feedback, speed up personalized learning, data sparsity and scalability, and achieve the effect of promoting development, improving relevance and accuracy
Pending Publication Date: 2021-06-18
BEIJING UNIV OF TECH
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] Traditional recommendation methods include collaborative filtering, content-based recommendation, and association rule-based recommendation. These methods all have their own advantages and disadvantages. The amount of feedback to speed up personalized learning; the ability to filter information that is difficult for automatic content analysis by machines; the disadvantages are: data sparsity issues and scalability issues
The advantages of content-based recommendation are: no cold start, new items, and data sparsity; it can be recommended for users with special interests; the disadvantage is: the recommended content must be able to abstract meaningful features and have good structural
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0023] The technical solution of the present invention will be described in detail below in conjunction with the accompanying drawings.
[0024] Such as figure 1 Shown is an answerer recommendation method for a community Q&A platform, which includes the following steps:
[0025] First, analyze and preprocess the original data downloaded from the Q&A community platform to extract the user reputation value of all users in the platform, the number of user homepage views, user ratings, user badges, user postings, user registration date, user last The user-related attribute values such as login date and user last activity date are specially stored in the data table of user data. Divide all posts on the platform into two categories: answers and questions, extract the titles, tags, text content, and owners of the posts, remove HTML tags and stop words from the text content of the posts, and process the processed The data of is stored exclusively in the data table of the post data...
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
Login to View More Abstract
The invention discloses an answerer recommendation method for a community question and answer platform. The method comprises the following steps that data is preprocessed, the related information data of all users in the platform is extracted, and the character preprocessing of the text content of a question and answer post is carried out; Jaccard similarity and TF-IDF cosine similarity are calculated according to titles, keywords, tags and text contents of questions proposed by a user, and question posts belonging to the same class with the questions are found out; answered users are found out in the classified posts, all the users answer questions similar to the original questions, the user information data according to the previously extracted user information data of the answers is analyzed to find out information which has a decisive effect on evaluating the user quality and the user answering tendency to serve as attribute characteristics of the users, and different weights are used for the attribute features; and the attribute values and the weights are accumulated and summed, and several answers with the highest numerical values are used as final recommendation results. The method can effectively help the questioner to find potential answers of the questions, and solves the problem that the questioner does not answer the questions for a long time.
Description
technical field [0001] The invention belongs to the technical field of recommendation, in particular to an answerer recommendation method for a community question answering platform. Background technique [0002] Traditional recommendation methods include collaborative filtering, content-based recommendation, and association rule-based recommendation. These methods all have their own advantages and disadvantages. The amount of feedback accelerates the speed of personalized learning; it can filter information that is difficult for automatic content analysis by machines; the disadvantages are: data sparsity problems and scalability problems. The advantages of content-based recommendation are: no cold start, new items, and data sparsity; it can be recommended for users with special interests; the disadvantage is: the recommended content must be able to abstract meaningful features and have good structural. Contents of the invention [0003] The present invention aims to sol...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/9535G06F16/9536G06F16/33G06F16/35G06F40/216G06Q50/00
CPCG06F16/9535G06F16/9536G06F16/3344G06F16/3346G06F16/3335G06F16/35G06F40/216G06Q50/01
Inventor 方胡彬高红雨苏航
Owner BEIJING UNIV OF TECH