What is the Message About? Automatic Multi-label Classification of Open Source Repository Messages into Content Types

DANIEL CAMPBELL

doi:10.1007/978-3-030-44289-7_49

What is the Message About? Automatic Multi-label Classification of Open Source Repository Messages into Content Types

DANIEL CAMPBELL

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding (ISBN) › peer-review

2 Citations (Scopus)

Abstract

Users of Open Source Software (OSS) projects discuss a diverse range of topics online. The content of a post often corresponds to one or more context-sensitive content types, e.g. a suggestion for a solution, a request for further clarification or indication that a proposed solution did not work. The detection of content types can provide several benefits for software developers. For instance, content types can be used as indicators that summarise the content of the messages. These indicators can be exploited as part of a developer-centric knowledge mining platform allowing developers and project managers to create action alerts concerning new bugs found outside of a bug tracker or they can be combined with other metrics to assess the quality of an OSS project. We present a multi-label classifier, able to classify messages exchanged on communication means about OSS, and detailed evaluation results. We experimented with two state-of-the-art multi-label classification approaches HOMER (Hierarchy Of Multilabel classifiER) and RAkEL (RAndom k-labELsets) as these met the technical requirements of the CROSSMINER project. A manually-annotated threaded corpus of posts form newsgroups discussions, bug tracking systems and forums related to Eclipse projects was also used. The results are promising and indicate the potential to attract novel and deeper research for this task.

Original language	English
Title of host publication	Proceedings of the International Conference on Artificial Intelligence and Computer Vision (AICV2020)
Editors	Aboul-Ella Hassanien, Ahmad Taher Azar, Tarek Gaber, Diego Oliva, Fahmy M. Tolba
Place of Publication	Cham
Publisher	Springer Nature Switzerland AG
Pages	520-531
Number of pages	12
ISBN (Electronic)	978-3-030-44289-7
ISBN (Print)	978-3-030-44288-0
DOIs	https://doi.org/10.1007/978-3-030-44289-7_49
Publication status	Published - 24 Mar 2020

Publication series

Name	Advances in Intelligent Systems and Computing
Publisher	Springer Nature
ISSN (Print)	2194-5357
ISSN (Electronic)	2194-5365

Keywords

Content classification
Information retrieval
Machine learning
Multi-label classification
Natural language
Open Source Software
Text mining

Access to Document

10.1007/978-3-030-44289-7_49

Cite this

CAMPBELL, DANIEL. (2020). What is the Message About? Automatic Multi-label Classification of Open Source Repository Messages into Content Types. In A.-E. Hassanien, A. Taher Azar, T. Gaber, D. Oliva, & F. M. Tolba (Eds.), Proceedings of the International Conference on Artificial Intelligence and Computer Vision (AICV2020) (pp. 520-531). (Advances in Intelligent Systems and Computing). Springer Nature Switzerland AG. https://doi.org/10.1007/978-3-030-44289-7_49

CAMPBELL, DANIEL. / What is the Message About? Automatic Multi-label Classification of Open Source Repository Messages into Content Types. Proceedings of the International Conference on Artificial Intelligence and Computer Vision (AICV2020). editor / Aboul-Ella Hassanien ; Ahmad Taher Azar ; Tarek Gaber ; Diego Oliva ; Fahmy M. Tolba. Cham : Springer Nature Switzerland AG, 2020. pp. 520-531 (Advances in Intelligent Systems and Computing).

@inproceedings{eabed9aae47843dcbef087c26aa3957c,

title = "What is the Message About? Automatic Multi-label Classification of Open Source Repository Messages into Content Types",

abstract = "Users of Open Source Software (OSS) projects discuss a diverse range of topics online. The content of a post often corresponds to one or more context-sensitive content types, e.g. a suggestion for a solution, a request for further clarification or indication that a proposed solution did not work. The detection of content types can provide several benefits for software developers. For instance, content types can be used as indicators that summarise the content of the messages. These indicators can be exploited as part of a developer-centric knowledge mining platform allowing developers and project managers to create action alerts concerning new bugs found outside of a bug tracker or they can be combined with other metrics to assess the quality of an OSS project. We present a multi-label classifier, able to classify messages exchanged on communication means about OSS, and detailed evaluation results. We experimented with two state-of-the-art multi-label classification approaches HOMER (Hierarchy Of Multilabel classifiER) and RAkEL (RAndom k-labELsets) as these met the technical requirements of the CROSSMINER project. A manually-annotated threaded corpus of posts form newsgroups discussions, bug tracking systems and forums related to Eclipse projects was also used. The results are promising and indicate the potential to attract novel and deeper research for this task.",

keywords = "Content classification, Information retrieval, Machine learning, Multi-label classification, Natural language, Open Source Software, Text mining",

author = "DANIEL CAMPBELL",

note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature Switzerland AG.",

year = "2020",

month = mar,

day = "24",

doi = "10.1007/978-3-030-44289-7_49",

language = "English",

isbn = "978-3-030-44288-0 ",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer Nature Switzerland AG",

pages = "520--531",

editor = "Hassanien, {Aboul-Ella } and {Taher Azar}, {Ahmad } and Gaber, {Tarek } and Oliva, {Diego } and Tolba, {Fahmy M. }",

booktitle = "Proceedings of the International Conference on Artificial Intelligence and Computer Vision (AICV2020)",

address = "Switzerland",

}

CAMPBELL, DANIEL 2020, What is the Message About? Automatic Multi-label Classification of Open Source Repository Messages into Content Types. in A-E Hassanien, A Taher Azar, T Gaber, D Oliva & FM Tolba (eds), Proceedings of the International Conference on Artificial Intelligence and Computer Vision (AICV2020). Advances in Intelligent Systems and Computing, Springer Nature Switzerland AG, Cham, pp. 520-531. https://doi.org/10.1007/978-3-030-44289-7_49

What is the Message About? Automatic Multi-label Classification of Open Source Repository Messages into Content Types. / CAMPBELL, DANIEL.
Proceedings of the International Conference on Artificial Intelligence and Computer Vision (AICV2020). ed. / Aboul-Ella Hassanien; Ahmad Taher Azar; Tarek Gaber; Diego Oliva; Fahmy M. Tolba. Cham: Springer Nature Switzerland AG, 2020. p. 520-531 (Advances in Intelligent Systems and Computing).

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding (ISBN) › peer-review

TY - GEN

T1 - What is the Message About? Automatic Multi-label Classification of Open Source Repository Messages into Content Types

AU - CAMPBELL, DANIEL

PY - 2020/3/24

Y1 - 2020/3/24

N2 - Users of Open Source Software (OSS) projects discuss a diverse range of topics online. The content of a post often corresponds to one or more context-sensitive content types, e.g. a suggestion for a solution, a request for further clarification or indication that a proposed solution did not work. The detection of content types can provide several benefits for software developers. For instance, content types can be used as indicators that summarise the content of the messages. These indicators can be exploited as part of a developer-centric knowledge mining platform allowing developers and project managers to create action alerts concerning new bugs found outside of a bug tracker or they can be combined with other metrics to assess the quality of an OSS project. We present a multi-label classifier, able to classify messages exchanged on communication means about OSS, and detailed evaluation results. We experimented with two state-of-the-art multi-label classification approaches HOMER (Hierarchy Of Multilabel classifiER) and RAkEL (RAndom k-labELsets) as these met the technical requirements of the CROSSMINER project. A manually-annotated threaded corpus of posts form newsgroups discussions, bug tracking systems and forums related to Eclipse projects was also used. The results are promising and indicate the potential to attract novel and deeper research for this task.

AB - Users of Open Source Software (OSS) projects discuss a diverse range of topics online. The content of a post often corresponds to one or more context-sensitive content types, e.g. a suggestion for a solution, a request for further clarification or indication that a proposed solution did not work. The detection of content types can provide several benefits for software developers. For instance, content types can be used as indicators that summarise the content of the messages. These indicators can be exploited as part of a developer-centric knowledge mining platform allowing developers and project managers to create action alerts concerning new bugs found outside of a bug tracker or they can be combined with other metrics to assess the quality of an OSS project. We present a multi-label classifier, able to classify messages exchanged on communication means about OSS, and detailed evaluation results. We experimented with two state-of-the-art multi-label classification approaches HOMER (Hierarchy Of Multilabel classifiER) and RAkEL (RAndom k-labELsets) as these met the technical requirements of the CROSSMINER project. A manually-annotated threaded corpus of posts form newsgroups discussions, bug tracking systems and forums related to Eclipse projects was also used. The results are promising and indicate the potential to attract novel and deeper research for this task.

KW - Content classification

KW - Information retrieval

KW - Machine learning

KW - Multi-label classification

KW - Natural language

KW - Open Source Software

KW - Text mining

UR - http://dx.doi.org/10.1007/978-3-030-44289-7_49

U2 - 10.1007/978-3-030-44289-7_49

DO - 10.1007/978-3-030-44289-7_49

M3 - Conference proceeding (ISBN)

SN - 978-3-030-44288-0

T3 - Advances in Intelligent Systems and Computing

SP - 520

EP - 531

BT - Proceedings of the International Conference on Artificial Intelligence and Computer Vision (AICV2020)

A2 - Hassanien, Aboul-Ella

A2 - Taher Azar, Ahmad

A2 - Gaber, Tarek

A2 - Oliva, Diego

A2 - Tolba, Fahmy M.

PB - Springer Nature Switzerland AG

CY - Cham

ER -

CAMPBELL DANIEL. What is the Message About? Automatic Multi-label Classification of Open Source Repository Messages into Content Types. In Hassanien AE, Taher Azar A, Gaber T, Oliva D, Tolba FM, editors, Proceedings of the International Conference on Artificial Intelligence and Computer Vision (AICV2020). Cham: Springer Nature Switzerland AG. 2020. p. 520-531. (Advances in Intelligent Systems and Computing). doi: 10.1007/978-3-030-44289-7_49

What is the Message About? Automatic Multi-label Classification of Open Source Repository Messages into Content Types

Abstract

Publication series

Keywords

Access to Document

Other files and links

Fingerprint

Cite this