SentTrack: Sentiment-Driven Bottleneck Detection in GitHub Issue Repositories

2026-06-09

AI Summary

This study addresses the challenge of early identification of socio-technical bottlenecks in open-source projects, which often arise from overlooked dynamics in issue discussions. The authors propose SentTrack, a dual-perspective framework that integrates a horizontal pipeline—leveraging large language models to clean and cluster issue content—with a vertical pipeline that classifies comments using the ABCDE collaborative interaction model to capture sentiment and stagnation signals indicative of high-friction discussions. This approach uniquely combines sentiment analysis with a structured model of collaborative interactions, effectively distinguishing human narrative signals from machine-generated noise and enabling earlier risk detection than conventional labeling methods. Evaluated on 9,000 issues from AvaloniaUI, the system revealed a 49% stagnation rate and 13% resolution rate, yielding an interpretable prioritization tool and extracting 613 semantic clusters.

Abstract

Software engineering teams increasingly depend on GitHub issue threads to coordinate work, report bugs, and negotiate technical decisions, yet most repository health tools focus on code metrics and ignore the conversational dynamics that drive or stall development. This paper presents SentTrack, a dual-lens framework for detecting socio-technical bottlenecks from GitHub issue discussions. Applied to the AvaloniaUI open-source repository across approximately 9,000 issue threads, the framework addresses three questions: how to automate workflow-inefficiency detection from real-time conversational data, whether sentiment signals can surface risk earlier than traditional label-based methods, and how to isolate human narrative from machine-generated noise in mixed-media issue text. SentTrack combines two complementary pipelines. A horizontal pipeline translates raw issue reports into clean summaries using a large language model, extracts mid-level concern phrases, and clusters them through UMAP and HDBSCAN, producing 613 semantic clusters from the first 3,608 issues processed. A vertical pipeline applies the ABCDE collaborative interaction framework to classify each comment and infer thread-level outcomes. Across the full corpus, 49\% of threads ended in stagnation and only 13\% reached resolution, with the resolution gap identified as the dominant bottleneck signal. A weighted scoring engine that combines negativity, stagnation, resolution gap, and thread length gives maintainers an interpretable prioritization tool for high-friction discussions before they stall development.

Problem

• bottleneck detection
• GitHub issue repositories
• sentiment analysis
• workflow inefficiency
• conversational dynamics

Innovation

• sentiment-driven bottleneck detection
• dual-lens framework
• large language model summarization
• collaborative interaction modeling
• workflow inefficiency prediction