User personalized label set extraction algorithm based on LDA and collaborative filtering in open source software community

Zhifang Liao, Tianhui Song, Yan Wang, Xiaoping Fan, Yan Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

As an open source project hosting platform, Github builds user-project heterogeneous networks with multiple user behaviors as a bridge. Users, as the core element in Github, guarantee the activity of the whole system. However, many new users have faced the problem that they don't know which repository suits them in a short period. This paper proposes an effective user personalized label extraction model based on LDA and collaborative filtering. This algorithm combines the familiarity of the user with the similarity of the user to obtain the user's personalized label set and applies the label set to the match the recommended scenario. The experiment shows that the algorithm has good recommendation effect and can alleviate the cold start problem of new users to a certain extent.

Original languageEnglish
Title of host publication2018 International Conference on Computer, Information and Telecommunication Systems (CITS)
EditorsMohammad S. Obaidat, Petros Nicopolitidis, Mohammad S. Obaidat, Pascal Lorenz, Kuei-Fang Hsiao, Mohammad S. Obaidat, Daniel Cascado-Caballero
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538645994
ISBN (Print)9781538640753, 9781538646007
DOIs
Publication statusPublished - 19 Aug 2018
Event2018 International Conference on Computer, Information and Telecommunication Systems - Colmar, France
Duration: 11 Jul 201813 Jul 2018

Publication series

NameCITS 2018 - 2018 International Conference on Computer, Information and Telecommunication Systems

Conference

Conference2018 International Conference on Computer, Information and Telecommunication Systems
Abbreviated titleCITS 2018
Country/TerritoryFrance
CityColmar
Period11/07/1813/07/18

Keywords

  • Github
  • Mining software repositories
  • User personalized label set

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Information Systems and Management
  • Health Informatics

Fingerprint

Dive into the research topics of 'User personalized label set extraction algorithm based on LDA and collaborative filtering in open source software community'. Together they form a unique fingerprint.

Cite this