publications

2026

1. ToxiShield: Promoting Inclusive Developer Communication through Real-Time Toxicity Filtering

   Md Awsaf Alam Anindya, Showvik Biswas, Anindya Iqbal, and 2 more authors

   Proc. ACM Softw. Eng., Jun 2026

   Abs DOI

   Toxic interactions during code reviews can undermine teamwork and hinder productivity in software engineering (SE) teams. While prior studies explore toxicity detection and empirical investigation, they lack real-time detoxification tools to support the SE community. To address this gap, we present ToxiShield, a browser extension for GitHub pull requests that is built using three modules: i) Toxicity Filter – to identify whether a text is toxic, ii) Communication coach – to facilitate just-in-time fine-grained toxicity categorization with explanations, and iii) The Reframer – that generates a revised, constructive alternative of a toxic text. For each module, we trained and evaluated multiple deep learning and Large Language Models (LLMs) to identify the best choice. A BERT-based binary detection model, trained on 38,761 code review samples, achieves 98% accuracy and an F1-score of 97% and is the selected one for the Toxicity Filter module. For the Communication Coach, prompt-tuned Claude 3.5 Sonnet achieved the best performance with 39% MCC and 42% F1 in multiclass toxicity classification with detailed reasoning. For Reframer, we evaluated five LLMs using a fine-tuning strategy on a dataset of 10,120 code review comments. The fine-tuned Llama 3.2 model achieves 95.27% style transfer accuracy, 97.03% fluency, 67.07% content preservation, and an 84% J-score. We further validated ToxiShield through a human evaluation using the Technology Acceptance Model with 10 participants, confirming its perceived usefulness and ease of adoption. ToxiShield sets a benchmark for advancing constructive communication in software engineering, driving inclusivity and healthier collaboration in open-source communities.

2. Real-Time Toxicity Filtering for Open-Source Code Reviews

   Md Awsaf Alam Anindya, Showvik Biswas, Anindya Iqbal, and 2 more authors

   arXiv preprint arXiv:2604.08886, Jun 2026

   arXiv

2025

1. A riverbank erosion early warning system (EWS-RE) for braided river: a case of the Brahmaputra–Jamuna

   Shampa, Hussain Muhammad Muktadir, Israt Jahan Nejhum, and 6 more authors

   Frontiers in Earth Science, Jun 2025

   Abs DOI HTML

   Braided rivers are distinguished by numerous bars and channels, along with their regular alterations. This unique character of braided rivers induces bank adjustment through erosion or accretion, and when erosion occurs in populated regions, it results in significant disasters. When such erosion affects inhabited areas, it can cause severe damage. To address this calamity, we introduce here an early warning system for riverbank erosion, named EWS-RE. This system issues alerts based on numerical simulations from a two-dimensional hydro-morphological model of the Brahmaputra–Jamuna River. The forecast model incorporates GloFAS seasonal forecasts and over six decades of historical hydraulic data to define boundary conditions. High-resolution bathymetry of the braided river was generated using an enhanced passive bathymetry technique, which combines satellite imagery with limited in-situ cross-sectional measurements. Model outputs and predicted erosion patterns were validated against actual riverbank changes observed in the year 2019. The system achieved a spatial erosion prediction accuracy of 88% and a sensitivity of 88%, both within a 95% confidence interval. Field testing in the year 2023 showed an overall accuracy of 70% in detecting erosion-prone areas along the river. We anticipate that this framework will contribute significantly to reducing the adverse impacts of riverbank erosion through timely and reliable early warnings.