What do Developers Know About Machine Learning: A Study of ML Discussions on StackOverflow

Bangash, Abdul Ali; Sahar, Hareem; Chowdhury, Shaiful Alam; Wong, Amy; Hindle, Abram; Ali, Karim

doi:10.1109/msr.2019.00052

Cited by 41 publications

(36 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers have conducted several studies based on the StackOverflow posts and bug reports of ML libraries. Abdul et al [14] observed that the most frequently discussed topics of Software-2.0 are ML algorithms, classification, and training data. Zhang et al [144] revealed that the top three most frequently asked questions in StackOverflow are program crashes, model migration, and implementation questions.…”

Section: Studies On Software-20mentioning

confidence: 99%

Understanding Software-2.0

Dilhara

Ketkar

Dig

2021

ACM Trans. Softw. Eng. Methodol.

View full text Add to dashboard Cite

Enabled by a rich ecosystem of Machine Learning (ML) libraries, programming using learned models , i.e., Software-2.0 , has gained substantial adoption. However, we do not know what challenges developers encounter when they use ML libraries. With this knowledge gap, researchers miss opportunities to contribute to new research directions, tool builders do not invest resources where automation is most needed, library designers cannot make informed decisions when releasing ML library versions, and developers fail to use common practices when using ML libraries. We present the first large-scale quantitative and qualitative empirical study to shed light on how developers in Software-2.0 use ML libraries, and how this evolution affects their code. Particularly, using static analysis we perform a longitudinal study of 3,340 top-rated open-source projects with 46,110 contributors. To further understand the challenges of ML library evolution, we survey 109 developers who introduce and evolve ML libraries. Using this rich dataset we reveal several novel findings. Among others, we found an increasing trend of using ML libraries: The ratio of new Python projects that use ML libraries increased from 2% in 2013 to 50% in 2018. We identify several usage patterns including the following: (i) 36% of the projects use multiple ML libraries to implement various stages of the ML workflows, (ii) developers update ML libraries more often than the traditional libraries , (iii) strict upgrades are the most popular for ML libraries among other update kinds, (iv) ML library updates often result in cascading library updates, and (v) ML libraries are often downgraded (22.04% of cases). We also observed unique challenges when evolving and maintaining Software-2.0 such as (i) binary incompatibility of trained ML models and (ii) benchmarking ML models. Finally, we present actionable implications of our findings for researchers, tool builders, developers, educators, library vendors, and hardware vendors.

show abstract

Section: Studies On Software-20mentioning

confidence: 99%

Understanding Software-2.0

Dilhara

Ketkar

Dig

2021

ACM Trans. Softw. Eng. Methodol.

View full text Add to dashboard Cite

show abstract

“…Orchestration simplifies the management of container clusters and their life-cycle. Docker supports various orchestration tools such as Mesos [20], Docker Swarm 10 , and Kubernetes 11 . Kubernetes is used extensively in comparison with other tools as indicated by [28] due to its compatibility with any operating system, auto-scaling feature for large deployments and better resource management facilities.…”

Section: 110mentioning

confidence: 99%

“…We also calculate the median time (in minutes) to receive an accepted answer for a question. The longer the time to receive an accepted answer can be explained as a more difficult question [4,5,8,11]. In addition, we use Kendall correlation [2] to identify and verify correlation between popular and difficult topics.…”

Section: Rq2 Topic Characteristics -What Are the Characteristics In mentioning

confidence: 99%

“…As aforementioned, many papers have investigated the software developers' perspectives by mining software repositories (eg, Github) and Q&A websites (eg, Sof). Some studies which leverage SoF data on different domains such as Machine Learning [5,11], Mobile [33], Security [23,42], Big data [8], Web development [9] and Concurrency [4]. Melo et al used Docker to reproduce codes derived from SoF posts.…”

Section: Related Workmentioning

confidence: 99%

“…An immense amount of knowledge is created within these communities, including question and answers on Docker technology, on configuration, troubleshooting, and various experiences. In the past, various works have turned to this vast repository of knowledge, using data mining techniques to understand the software developers' perspectives on various matters, such as DevOps [43], Machine Learning (ML) [5,11], Big Data [8], and software security [42].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Challenges in Docker Development

Haque¹,

Iwaya²,

Babar³

2020

Proceedings of the 14th ACM / IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM)

View full text Add to dashboard Cite

Background: Docker technology has been increasingly used among software developers in a multitude of projects. This growing interest is due to the fact that Docker technology supports a convenient process for creating and building containers, promoting close cooperation between developer and operations teams, and enabling continuous software delivery. As a fast-growing technology, it is important to identify the Docker-related topics that are most popular as well as existing challenges and difficulties that developers face. Aims: This paper presents a large-scale empirical study identifying practitioners' perspectives on Docker technology by mining posts from the Stack Overflow (SoF) community. Method: A dataset of 113, 922 Docker-related posts was created based on a set of relevant tags and contents. The dataset was cleaned and prepared. Topic modelling was conducted using Latent Dirichlet Allocation (LDA), allowing the identification of dominant topics in the domain. Results: Our results show that most developers use SoF to ask about a broad spectrum of Docker topics including framework development, application deployment, continuous integration, web-server configuration and many more. We determined that 30 topics that developers discuss can be grouped into 13 main categories. Most of the posts belong to categories of application development, configuration, and networking. On the other hand, we find that the posts on monitoring status, transferring data, and authenticating users are more popular among developers compared to the other topics. Specifically, developers face challenges in web browser issues, networking error and memory management. Besides, there is a lack of experts in this domain. Conclusion: Our research findings will guide future work on the development of new tools and techniques, helping the community to focus efforts and understand existing trade-offs on Docker topics. CCS CONCEPTS • General and reference → Empirical studies; • Computing methodologies → Information extraction.

show abstract

Mining software architecture knowledge: Classifying stack overflow posts using machine learning

Ali

Mushtaq

Rasheed

et al. 2021

Concurrency and Computation

View full text Add to dashboard Cite

Software Architectural Process (SAP) is a core and excessively knowledge intensive phase of software development life cycle, as it consumes and produces knowledge artifacts, simultaneously. SAP is about making design decisions, and the changes in these verdicts may pose adverse effects on software projects. The performance and properties of software components are fundamentally influenced by the design decisions.The implementation of immature and abrupt design decisions seriously threatens the development process of SAP. Moreover, software architectural knowledge management (AKM) approaches offer systematic ways to support SAP through versatile architectural solutions and design decisions. However, the majority of software organizations have limited access to data and still depend upon manually created and maintained AKM process. In this paper, we have utilized the one of the most prominent online community for software development (i.e., Stack Overflow) as a source of SAP knowledge to support AKM. In order to support AKM, we have proposed a supervised machine learning-based approach to classify the architectural knowledge into predefined categories, that is, analysis, synthesis, evaluation, and implementation. We have employed different combinations of feature selection technique to achieve the optimal classification results of the used classifiers (Support Vector Machine [SVM], K-Nearest Neighbor, Random Forest, and Naive Bayes [NB]). Among these classifiers, SVM with Uni-gram feature set provides best classification results and attains 85.80% accuracy.For evaluating the proposed approach's effectiveness, we have also computed the suitability of the classifiers, that is, the cost of computation along with its accuracy, and NB with Uni-gram feature set proved to be the most suitable. K E Y W O R D Sarchitectural knowledge management, stack overflow, crowd-sourced communities, text mining, classification INTRODUCTIONSoftware architectural design appears to have a significant importance in Software Development Life Cycle (SDLC). Its manifests are the early design decisions which help to determine the system development, deployment, and evaluation. To develop a quality project, better architectural decisions are essential and these decisions pose vast challenges for software engineers. Architectural Knowledge Management (AKM) is used to capture

show abstract

What do Developers Know About Machine Learning: A Study of ML Discussions on StackOverflow

Cited by 41 publications

References 6 publications

Understanding Software-2.0

Understanding Software-2.0

Challenges in Docker Development

Mining software architecture knowledge: Classifying stack overflow posts using machine learning

Contact Info

Product

Resources

About