Predicting Popularity of Open Source Projects Using Recurrent Neural Networks

Sefa Eren Sahin*, Kubilay Karpat, Ayse Tosun

*Bu çalışma için yazışmadan sorumlu yazar

Araştırma sonucu: ???type-name???Konferans katkısıbilirkişi

7 Atıf (Scopus)

Özet

GitHub is the largest open source software development platform with millions of repositories on variety of topics. The number of stars received by a repository is often considered as a measure of its popularity. Predicting the number of stars of a repository has been associated with the number of forks, commits, followers, documentation size, and programming language in the literature. We extend prior studies in terms of input features and algorithm: We define six features from GitHub events corresponding to the development activities, and additional six features incorporating the influence of users (followers and contributors) on the popularity of projects into their development activities. We propose a time-series based forecast model using Recurrent Neural Networks to predict the number of stars received in consecutive k days. We assess the performance of our proposed model with varying k (1, 7, 14, 30 days) and with varying input features. Our analysis on five topmost starred repositories in data visualization area shows that the error rate ranges between 19.76 and 70.57 among the projects. The best performing models use either features from development activities only, or all metrics including all the features.

Orijinal dilİngilizce
Ana bilgisayar yayını başlığıOpen Source Systems - 15th IFIP WG 2.13 International Conference, OSS 2019, Proceedings
EditörlerFrancis Bordeleau, Alberto Sillitti, Paulo Meirelles, Valentina Lenarduzzi
YayınlayanSpringer New York LLC
Sayfalar80-90
Sayfa sayısı11
ISBN (Basılı)9783030208820
DOI'lar
Yayın durumuYayınlandı - 2019
Etkinlik15th International Conference on Open Source Systems, OSS 2019 - Montreal, Canada
Süre: 26 May 201927 May 2019

Yayın serisi

AdıIFIP Advances in Information and Communication Technology
Hacim556
ISSN (Basılı)1868-4238
ISSN (Elektronik)1868-422X

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???15th International Conference on Open Source Systems, OSS 2019
Ülke/BölgeCanada
ŞehirMontreal
Periyot26/05/1927/05/19

Bibliyografik not

Publisher Copyright:
© IFIP International Federation for Information Processing 2019.

Finansman

Acknowledgments. This research is supported in part by Scientific Research Projects Division of Istanbul Technical University with project number MGA-2017-40712 and Scientific and Technological Research Council of Turkey with project number 5170048.

FinansörlerFinansör numarası
Türkiye Bilimsel ve Teknolojik Araştirma Kurumu5170048
Istanbul Teknik ÜniversitesiMGA-2017-40712

    Parmak izi

    Predicting Popularity of Open Source Projects Using Recurrent Neural Networks' araştırma başlıklarına git. Birlikte benzersiz bir parmak izi oluştururlar.

    Alıntı Yap