arXiv subjects

Mehdi Golzadeh

Publications and source records attributed to Mehdi Golzadeh.

4 recordsLinked to original sources

arXiv2022

Leveraging Predictions from Multiple Repositories to Improve Bot Detection

Contemporary social coding platforms such as GitHub facilitate collaborative distributed software development. Developers engaged in these platforms often use machine accounts (bots) for automating effort-intensive or repetitive activities. Determining whether a contributor corresponds to a bot or a human account is important in socio-technical studies, for example, to assess the positive and negative impact of using bots, analyse the evolution of bots and their usage, identify top human contributors, and so on. BoDeGHa is one of the bot detection tools that have been proposed in the literature. It relies on comment activity within a single repository to predict whether an account is driven by a bot or by a human. This paper presents preliminary results on how the effectiveness of BoDeGHa can be improved by combining the predictions obtained from many repositories at once. We found that doing this not only increases the number of cases for which a prediction can be made but that many diverging predictions can be fixed this way. These promising, albeit preliminary, results suggest that the "wisdom of the crowd" principle can improve the effectiveness of bot detection tools.

cs.SE↗

arXiv2021

Evaluating a bot detection model on git commit messages

Detecting the presence of bots in distributed software development activity is very important in order to prevent bias in large-scale socio-technical empirical analyses. In previous work, we proposed a classification model to detect bots in GitHub repositories based on the pull request and issue comments of GitHub accounts. The current study generalises the approach to git contributors based on their commit messages. We train and evaluate the classification model on a large dataset of 6,922 git contributors. The original model based on pull request and issue comments obtained a precision of 0.77 on this dataset. Retraining the classification model on git commit messages increased the precision to 0.80. As a proof-of-concept, we implemented this model in BoDeGiC, an open source command-line tool to detect bots in git repositories.

cs.SE↗

arXiv2021

Identifying bot activity in GitHub pull request and issue comments

Development bots are used on Github to automate repetitive activities. Such bots communicate with human actors via issue comments and pull request comments. Identifying such bot comments allows preventing bias in socio-technical studies related to software development. To automate their identification, we propose a classification model based on natural language processing. Starting from a balanced ground-truth dataset of 19,282 PR and issue comments, we encode the comments as vectors using a combination of the bag of words and TF-IDF techniques. We train a range of binary classifiers to predict the type of comment (human or bot) based on this vector representation. A multinomial Naive Bayes classifier provides the best results. Its performance on a test set containing 50% of the data achieves an average precision, recall, and F1 score of 0.88. Although the model shows a promising result on the pull request and issue comments, further work is required to generalize the model on other types of activities, like commit messages and code reviews.

cs.SE↗

arXiv2021

A ground-truth dataset and classification model for detecting bots in GitHub issue and PR comments

Bots are frequently used in Github repositories to automate repetitive activities that are part of the distributed software development process. They communicate with human actors through comments. While detecting their presence is important for many reasons, no large and representative ground-truth dataset is available, nor are classification models to detect and validate bots on the basis of such a dataset. This paper proposes a ground-truth dataset, based on a manual analysis with high interrater agreement, of pull request and issue comments in 5,000 distinct Github accounts of which 527 have been identified as bots. Using this dataset we propose an automated classification model to detect bots, taking as main features the number of empty and non-empty comments of each account, the number of comment patterns, and the inequality between comments within comment patterns. We obtained a very high weighted average precision, recall and F1-score of 0.98 on a test set containing 40% of the data. We integrated the classification model into an open source command-line tool to allow practitioners to detect which accounts in a given Github repository actually correspond to bots.

cs.SE↗