Mining Software Repositories (MSR), 2026

Shojibur Rahman, MD Fazle Rabbi and Minhaz Zibran

In this paper, we present a comparative study of five autonomous coding agents using AIDev-pop, which is a public dataset containing thousands of AI-generated pull requests (PRs) across popular open-source repositories. We evaluate agents' performance along three task-aware dimensions spanning the PR lifecycle: (1) PR acceptance rate, (2) review discussion volume, and (3) commit message quality. Our quantitative analysis finds that Codex consistently achieves high PR acceptance rates across most task categories, while Copilot's PRs trigger the highest volume of both human and automated review discussions. In contrast, commit-level quality varies independently of acceptance outcomes. Claude and Cursor produce higher proportions of high-quality commit messages across several task types, and Codex exhibiting comparatively lower commit quality despite strong integration outcomes. Our findings inform selection and improvements of AI agents for their effective integration to collaborative software engineering. Link

21st International Conference on Information Technology-New Generations, 2024

Rifat Ara Tasnim and Farjana Z. Eishita

In modern video games, music has become an unavoidable component. Previous research showed that to fabricate the connection between games and players, music is inevitable. While it has been widely accepted that music has the power to impact people’s minds, it is yet to discover the differential impact of distinct categories of tunes on players’ gameplay experience. In this paper, we have conducted a controlled experiment to investigate the impact of different in-game background music on the gameplay experience. We hypothesized that, different background music will deferentially impact players’ gameplay experiences. Aligned with our hypothesis, the experimental outcome demonstrated that our three original music—Fruit Drop, Iced, and Soar have a distinctive impact on an individual’s gameplay experience. Link

10th International Conference on Serious Games and Applications for Health (SeGAH). IEEE, 2022

Rifat Ara Tasnim and Farjana Z. Eishita

Cognitive Distortion, defined as erroneous and inaccurate thoughts [4] can cause fatal mental impairment. Identifying the presence of cognitive distortions is the fundamental initiative to treat mental health disorders such as anxiety and depression. As a consequence of COVID-19 and the other changes in social aspects, there is an escalation in the number of patients with mental illness. Although there are abundant effective psychotherapy strategies available, a substantial number of people avoid them due to misconceptions and stigma. Serious games can be a feasible solution to purvey mental healthcare to a significant percentage of people. The availability of smartphones unveils the opportunity to provide therapeutic facilities via digital gaming. Technology like Augmented Reality with its interactive features, has unlocked numerous opportunities in the mental health domain. In this paper, we have remodeled our previously proposed game, ARCoD, accessible on smartphones to measure Cognitive Distortions. We hypothesized that, through this game, it is possible to assess the level of 5 different Cognitive Distortions (Arbitrary Inference, Catastrophizing, Black and White Thinking, Emotional Reasoning, and Labeling) in an individual playing the game. The experimental outcome demonstrates that the level of Cognitive Distortions assessed from the game is exceedingly similar to the measurement accumulated from an established scale- Cognitive Distortion Scale (CDS). Link