Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Launch Supplement

Queen's University

$12,500.00

Developing Actionable Diversity and Inclusion Tools and Systems for a Socio-Technically Sustainable Open Source.

EF 2024-25

Résumé
Open Source Software (OSS) has become an integral part of modern software development, underpinning diverse applications from personal use to critical infrastructure. Yet, the glaring lack of diversity and inclusion remains a profound concern. Participation by women in OSS projects is strikingly low, accounting for less than 12% which is less than half of their representation in software industry (i.e., 24%). Additionally, a significant proportion of newcomers do not transition to long-term contributors. The implications of this lack of diversity are multifaceted, including a missed opportunity for diverse perspectives, a loss of skill-building and experience for underrepresented groups, and potential job opportunities tied to OSS contributions. Moreover, over-reliance on a limited set of contributors can stifle innovation and increase turnover, threatening the sustainability of OSS projects. The goal of this research proposal is to develop technical solutions (i.e., actionable recommendation systems) to retain contributors in OSS, especially those in underrepresented groups. Two threads will be explored: one focusing on contributors and the other on project maintainers. The former will focus on empirically evidenced feature engineering to personalize OSS contributions based on individual needs and motivations. The latter will provide maintainers with project and community facing EDI recommendations to inform decision-making. The proposal combines Software Engineering and Human-Computer Interaction (HCI) methods to build user-centric and empirically-driven technical solutions. Machine Learning Models and Recommender Systems will be adapted to lower contribution barriers and personalize recommendations to contributors' unique needs (e.g., skills, cognitive styles of learning) and motivations (e.g., reputation, altruism). These systems calculate similarity scores (e.g., cosine similarity) to ensure the relevance of the recommendations. Through a participatory design approach we will actively engage with contributors and maintainers in the creation and evaluation of these solutions, promoting user-centricity and increasing solution acceptance. Additionally, predictive modeling, including forecasting contributors' churn will be leveraged as the basis of community-facing recommendation. The novelty of this proposed research is in developing actionable EDI recommendation systems for OSS-a complex setting that mixes volunteers and paid contributors from a variety of backgrounds in an environment shown to be discouraging to women and minority groups. By developing effective recommendation tools, we aim to empower contributors from all backgrounds to thrive in OSS projects. Ultimately, this research benefits the Canadian and global society by making OSS more inclusive, diverse, and sustainable. The importance of an inclusive open source cannot be understated, as OSS affects almost every aspect of modern life and economic growth.
Programme
Discovery Launch Supplement
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
DGECR-2024-00103
Name nom
Guizani, Mariam
Department département
Electrical and Computer Engineering
Organization id
29
Institution établissement
Queen's University
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
12500
Program id
DGECR
Program name en
Discovery Launch Supplement
Program name fr
Supplément Tremplin vers la découverte
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
Research subject code
2706
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Software engineering
Research subject fr
Génie logiciel
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Developing Actionable Diversity and Inclusion Tools and Systems for a Socio-Technically Sustainable Open Source.
Keywords
software engineering; open source software; equity, diversity, and inclusion; recommender systems; human factors; human-computer interaction
Application summary
Open Source Software (OSS) has become an integral part of modern software development, underpinning diverse applications from personal use to critical infrastructure. Yet, the glaring lack of diversity and inclusion remains a profound concern. Participation by women in OSS projects is strikingly low, accounting for less than 12% which is less than half of their representation in software industry (i.e., 24%). Additionally, a significant proportion of newcomers do not transition to long-term contributors. The implications of this lack of diversity are multifaceted, including a missed opportunity for diverse perspectives, a loss of skill-building and experience for underrepresented groups, and potential job opportunities tied to OSS contributions. Moreover, over-reliance on a limited set of contributors can stifle innovation and increase turnover, threatening the sustainability of OSS projects. The goal of this research proposal is to develop technical solutions (i.e., actionable recommendation systems) to retain contributors in OSS, especially those in underrepresented groups. Two threads will be explored: one focusing on contributors and the other on project maintainers. The former will focus on empirically evidenced feature engineering to personalize OSS contributions based on individual needs and motivations. The latter will provide maintainers with project and community facing EDI recommendations to inform decision-making. The proposal combines Software Engineering and Human-Computer Interaction (HCI) methods to build user-centric and empirically-driven technical solutions. Machine Learning Models and Recommender Systems will be adapted to lower contribution barriers and personalize recommendations to contributors' unique needs (e.g., skills, cognitive styles of learning) and motivations (e.g., reputation, altruism). These systems calculate similarity scores (e.g., cosine similarity) to ensure the relevance of the recommendations. Through a participatory design approach we will actively engage with contributors and maintainers in the creation and evaluation of these solutions, promoting user-centricity and increasing solution acceptance. Additionally, predictive modeling, including forecasting contributors' churn will be leveraged as the basis of community-facing recommendation. The novelty of this proposed research is in developing actionable EDI recommendation systems for OSS-a complex setting that mixes volunteers and paid contributors from a variety of backgrounds in an environment shown to be discouraging to women and minority groups. By developing effective recommendation tools, we aim to empower contributors from all backgrounds to thrive in OSS projects. Ultimately, this research benefits the Canadian and global society by making OSS more inclusive, diverse, and sustainable. The importance of an inclusive open source cannot be understated, as OSS affects almost every aspect of modern life and economic growth.