SentTrack: Sentiment-Driven Bottleneck Detection in GitHub Issue Repositories

• URL: http://arxiv.org/abs/2606.11476v1
• Date: Tue, 09 Jun 2026 22:12:41 GMT
• Title: SentTrack: Sentiment-Driven Bottleneck Detection in GitHub Issue Repositories
• Abstract summary: SentTrack is a framework for detecting socio-technical bottlenecks from GitHub issue discussions.<n>It is applied to the AvaloniaUI open-source repository across approximately 9,000 issue threads.
• Score: 4.18477469430107
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Maintenance and Support in Community-Driven Scientific Pipeline Ecosystems: A Cross-Platform Empirical Study of nf-core [3.9933521189187693]
  This paper presents a cross-platform empirical study of maintenance and support in nf-core, a large ecosystem of standardized Nextflow pipelines.<n>We analyze 15,760 GitHub issues, 35,411 GitHub pull requests, and 895 Seqera Community Forum discussions to examine what maintenance and support concerns arise.
  arXiv  Detail & Related papers  (2026-07-12T17:05:07Z)
• From Threads to Trajectories: A Multi-LLM Pipeline for Community Knowledge Extraction from GitHub Issue Discussions [5.590965631053725]
  We present SWE-MIMIC-Bench, an issue trajectory dataset generated from raw GitHub discussions.<n>Unlike simple summarization, this pipeline utilizes a group of closed-source LLMs to perform granular tasks.<n>We evaluated our system on 800 real-world GitHub issues drawn from the SWE-Bench-Pro, SWE-Bench-Multilingual and SWE-Bench-Verified dataset.
  arXiv  Detail & Related papers  (2026-04-28T17:21:46Z)
• SinkTrack: Attention Sink based Context Anchoring for Large Language Models [57.87121346197518]
  Large language models (LLMs) suffer from hallucination and context forgetting.<n>SinkTrack treats BOS> as an information anchor and injects key contextual features into its representation.<n>SinkTrack is training-free, plug-and-play, and introduces negligible inference overhead.
  arXiv  Detail & Related papers  (2026-04-11T04:49:11Z)
• Toxicity Ahead: Forecasting Conversational Derailment on GitHub [9.862809084820304]
  Toxic interactions in Open Source Software (OSS) communities reduce contributor engagement and threaten project sustainability.<n>To support more scalable approaches, we curate a dataset of 159 derailed toxic threads and 207 non-toxic threads from GitHub discussions.<n>We present a novel Large Language Model (LLM)-based framework for predicting conversational derailment on GitHub using a two-step prompting pipeline.
  arXiv  Detail & Related papers  (2025-12-17T02:45:12Z)
• Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning [102.13989674248116]
  ThinkMerge is a training-free, plug-and-play decoding strategy.<n>It runs K parallel reasoning traces and averages their next-token logits at synchronization points to produce a single coherent output.
  arXiv  Detail & Related papers  (2025-12-02T15:35:31Z)
• TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework [62.66056331998838]
  TeaRAG is a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps.<n>Our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps.
  arXiv  Detail & Related papers  (2025-11-07T16:08:34Z)
• VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detection [67.09867723723934]
  3D semantic occupancy prediction aims to reconstruct the 3D geometry and semantics of the surrounding environment.<n>With dense voxel labels, prior works typically formulate it as a dense segmentation task, independently classifying each voxel.<n>We propose VoxDet, an instance-centric framework that reformulates the voxel-level occupancy prediction as dense object detection.
  arXiv  Detail & Related papers  (2025-06-05T04:31:55Z)
• SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving [90.32201622392137]
  We present SwingArena, a competitive evaluation framework for Large Language Models (LLMs)<n>Unlike traditional static benchmarks, SwingArena models the collaborative process of software by pairing LLMs as iterations, who generate patches, and reviewers, who create test cases and verify the patches through continuous integration (CI) pipelines.
  arXiv  Detail & Related papers  (2025-05-29T18:28:02Z)
• Beyond Final Code: A Process-Oriented Error Analysis of Software Development Agents in Real-World GitHub Scenarios [31.749442120603774]
  Python execution errors during the issue resolution phase correlate with lower resolution rates and increased reasoning overheads.<n>We have identified the most prevalent errors -- such as ModuleNotFoundError and TypeError -- and highlighted particularly challenging errors like OSError and database-related issues.
  arXiv  Detail & Related papers  (2025-03-16T06:24:51Z)
• Looking for related discussions on GitHub Discussions [18.688096673390586]
  GitHub Discussions is a native forum to facilitate collaborative discussions between users and members of communities hosted on the platform. As GitHub Discussions resembles PCQA forums, it faces challenges similar to those faced by such environments. While duplicate posts have the same content - and may be exact copies - near-duplicates share similar topics and information. We propose an approach based on a Sentence-BERT pre-trained model: the RD-Detector.
  arXiv  Detail & Related papers  (2022-06-23T20:41:33Z)
• A Transfer Learning Approach for Dialogue Act Classification of GitHub Issue Comments [1.370633147306388]
  This paper presents a transfer learning approach for performing dialogue act classification on issue comments on GitHub. Since no large labeled corpus of GitHub issue comments exists, employing transfer learning enables us to leverage standard dialogue act datasets. Being able to map the issue comments to dialogue acts is a useful stepping stone towards understanding cognitive team processes.
  arXiv  Detail & Related papers  (2020-11-10T02:56:18Z)
• Integrating end-to-end neural and clustering-based diarization: Getting the best of both worlds [71.36164750147827]
  Clustering-based approaches assign speaker labels to speech regions by clustering speaker embeddings such as x-vectors. End-to-end neural diarization (EEND) directly predicts diarization labels using a neural network. We propose a simple but effective hybrid diarization framework that works with overlapped speech and for long recordings containing an arbitrary number of speakers.
  arXiv  Detail & Related papers  (2020-10-26T06:33:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.