BRMDS: an LLM-based multi-dimensional summary generation approach for bug reports

The goal of this study is to use summary generation and topic modeling to identify factors contributing to vaccine attitudes for three different vaccine brands, with the aim of generalizing these factors across different regions. A total of 5562 tweets about three vaccine brands (Sinovac, AstraZeneca, and Pfizer) were collected from 14 December 2020 to 30 December 2021. BERTopic clustering is used to group the tweets into topics, and then contrastive learning (CL) is adopted to generate summaries of each topic. The main content of each topic is generalized into three factors that contribute to vaccine attitudes: vaccine-related factors, health system-related factors, and individual social attributes. BERTopic clustering outperforms Latent Dirichlet Allocation clustering in our analysis. It can also be found that using CL for summary generation helped to better model the topics, particularly at the center-point of the clustering. Our model identifies three main factors contributing to vaccine attitudes that are consistent across different regions. Our study demonstrates the effectiveness of deep learning methods for identifying factors contributing to vaccine attitudes in different regions. By determining these factors, policymakers and medical institutions can develop more effective strategies for addressing concerns related to the vaccination process.

When debugging large-scale software systems, manually identifying relevant log portions for root-cause analysis is inefficient. Existing approaches are limited to detecting anomalies, extracting key error lines, or summarizing logs for root-cause analysis, and do not explicitly recommend which contiguous log ranges developers should review. Efficient debugging requires an approach that recommends log sections for prioritized review. This paper presents a formalization of the log-range recommendation (LRR) problem and proposes a two-stage pipeline called Log Retrieval with Intelligent Decomposition and Narrowing (LORIN). Pipeline (1) reduces the search space through anomaly detection, and pipeline (2) provides range extraction and evidence-based responses through a retrieval-augmented generation (RAG) approach that combines query decomposition with iterative refinement. To address LRR, a newly defined problem without established benchmarks, we validated the feasibility of LORIN through an exploratory multiple-case study of 30 Android Open-Source Project (AOSP) bug reports (averaging 10,445 lines). By varying the context buffer lines surrounding the recommendations across seven configurations, we observed a coverage–alignment tradeoff, where coverage improved from 66.4% to 89.9%, and intersection-over-union (IoU) score decreased from 17.8% to 4.8%. The findings of this study provide a formalization of the LRR problem and an evaluation protocol, establishing a methodological starting point for future research across diverse domains and large-scale datasets.

Critical information related to a software developer'scurrent task is trapped in technical developer discussions,bug reports, code reviews, and other software artefacts. Muchof this information pertains to the proper use of code elements(e.g., methods and classes) that capture vital problem domainknowledge. To understand the purpose of these code elements,software developers must either access documentation and onlineposts and understand the source code or peruse a substantialamount of text. In this paper, we use the context that surroundscode elements in StackOverflow posts to summarize the use andpurpose of code elements. To provide focus to our investigation,we consider the generation of summaries for library identifiersdiscussed in StackOverflow. Our automatic summarization approachwas evaluated on a sample of 100 randomly-selectedlibrary identifiers with respect to a benchmark of summariesprovided by two annotators. The results show that the approachattains an R-precision of 54%, which is appropriate given thediverse ways in which code elements can be used.

Acknowledgements Preface List of Abbreviations Introduction Order, Security and Conflict in a Changing Global Environment First Generation Approaches to Ending Conflict Second Generation Approaches to Ending Conflict Critiquing First and Second Generation Approaches in the Contemporary Context Third Generation of Multi-dimensional Approaches to Ending Conflict Conclusion: Rethinking Approaches to Ending Conflict Appendices Index

With the exponential growth of the internet, a lot of online news reports are produced on the web every day. The news stream flows so rapidly that no one has the time to look at each and every item of information. In this situation, a person would naturally prefer to read updated information at certain time intervals. Document updating technique is very helpful for individuals to acquire new information or knowledge by eliminating out-of-date or redundant information. Existing summarization systems involve identifying the most relevant sentences from the text and putting them together to create a concise initial summary. In the process of identifying the important sentences, features influencing the relevance of sentences are determined. Based on these features the salience of the sentence is calculated and an initial summary is generated from highly important sentences at different compression rates. These types of initial summaries work on a batch of documents and do not consider the documents that may arrive at later time, so that corresponding summaries need to get updated. The update summarization system addresses this issue by taking into account the documents read by the user in the past and seeks to present only fresh or different information. The first step is to create an initial summary based on basic and additional features. The next step is to create an update summary based on the basic, additional and update features. In this paper, two approaches are proposed for generating initial and update summary from multiple documents about given news. The first approach performs semantic analysis by modifying the vector space model with dependency parse relations and applying latent semantic analysis on it to create a summary. The second approach applies sentence annotation based on aspects, prepositions and named entities to generate summary. Experimental results show that the proposed approaches generate better initial and update summaries compared with the existing systems.