Github open source project recommendation method based on sparse autoencoder

Abstract

The present invention discloses a Github open source project recommendation method based on a sparse autoencoder. The method comprises: preprocessing data from three dimensions of a project, a user, and a project-user, and obtaining a user association degree matrix, a project association degree matrix, and a user-project association degree matrix; extracting textual information and clustering projects by analyzing text similarity; combining a collaborative filtering model and a sparse autoencoder to help developers find suitable open source projects; and taking the three matrices obtained by data preprocessing as input, obtaining two potential factor vectors through iterative neural network learning, predicting missing items in the user-project association degree matrix through the inner product of the potential factor vectors, and recommending the top N items with higher scores in the same category according to the clustering information of the open source project. According to the method disclosed by the present invention, suitable projects are recommended to the developers, the time taken by the developers to find interestied projects in massive open source projects is saved, and the performance of the developers participating in the open source projects is improved.

Description

technical field [0001] The invention relates to a Github open source project recommendation method based on a sparse autoencoder, and belongs to the technical fields of software engineering recommendation systems and data mining. Background technique [0002] Github is today's largest hosting platform for open source and proprietary software projects, and developers use it to realize social programming. The openness and flexibility of Githhub have enabled more and more software development enthusiasts to join this community, forming a huge software productivity. In the Github open source community, developers can follow other developers, bookmark or follow open source projects they are interested in, and clone projects locally for modification and updates. This enables code collaboration to be realized in different regions at different times. With the continuous growth of open source resources, a lot of reusable software has been brought to software development. But at th...

AI Technical Summary

Problems solved by technology

However, the social connection between developers has not been further explored, and the consideration of the characteristic attributes associated with developers and open source projects is relatively simple, and the valuable characteristics in user historical behavior data have not been fully utilized.

[0004] At the same time, it is not appropriate to use traditional recommendation algorithms to recommend suitable open source projects for developers.

First of all, the data in Github is extremely sparse. As far as open source projects are concerned, most open source projects only involve individual developers, and many open source projects

Images