Search

Software engineers post their opinions about various topics on social media that can be collectively mined using Sentiment Analysis. Analyzing this opinion is useful because it can provide insight into developers' feedback about various tools and topics. General-purpose sentiment analysis tools do not work well in the software domain because most of these tools are trained on movies and review datasets. Therefore, efforts are underway to develop domain-specific sentiment analysis tools for the Software Engineering (SE) domain. However, existing domain-specific tools for SE struggle to compute negative and neutral sentiments and can not be used on all SE datasets. This work uses a hybrid technique based on deep learning and a fine-tuned BERT model, i.e., Bert-Base, Bert-Large, Bert-LSTM, Bert-GRU, and Bert-CNN presented that is adapted as a domain-specific sentiment analysis tool for Community Question Answering datasets (named as Fuzzy Ensemble). Five different variants of fine-tuned BERT on the SE dataset are developed, and an ensemble of these fine-tuned models is taken using fuzzy logic. The trained model is evaluated on four publicly available benchmark datasets, i.e., Stack Overflow, JavaLib, Jira, and Code Review, using various evaluation metrics. The fuzzy Ensemble model is also compared with the state-of-the-art sentiment analysis tools for the software engineering domain, i.e., SentiStrength-SE, Senti4SD, SentiCR, and Generative Pre-Training Transformer (GPT). GPT mode is fine-tuned by the authors for domain-specific sentiment analysis. The Fuzzy Ensemble model covers the limitation of existing tools and improve accuracy to predict neutral sentiments even on diverse dataset. The fuzzy Ensemble model performs superior to state-of-the-art tools by achieving a maximum F1-score of 0.883. [ABSTRACT FROM AUTHOR]

The semantic-based method for question retrieval is an important method for searching similar questions in community question answering (CQA). The major challenges in question retrieval lie in polysemy and lexical gaps between questions, and the quality of retrieved similar questions by semantic retrieval model might not be high enough to effectively solve one's doubts. In order to address these challenges, a high-quality and multi-level semantic analysis-based similar question retrieval framework named HQML-QR is proposed, which consists of semantic representation from tag-level and sentence-level semantics for question retrieval (TS-QR) and multi-dimensional quality analysis (MDQQ). Firstly, TS-QR extracts multi-level semantic features of the question contents, where graph embedding model is utilized to learn coarse-grained semantics of questions from the scope of the tag. Meanwhile, in order to effectively identify polysemy and extract fine-grained sentence semantic of questions, TS-QR integrates the pre-trained language model based on self-attention mechanism to ensure the accuracy of question retrieval. Secondly, based on the quality factors in CQA (i.e., popularity, question, answer and user), MDQQ constructs a multi-dimensional quality evaluation model to provide a reasonable quality measurement standard for questions. Under the guidance of the quality of questions, the similarity score obtained by semantic vector matching is updated to retrieve high-quality and semantically similar questions. Finally, experiments are executed on CQADupStack dataset from Stack Overflow and the experimental results show that the P@N of HQML-QR has an average increase of 5.65%, 4.44% and 4.34% compared with LDA-VSM-SEM, WET-QR, RCM-QR, respectively. [ABSTRACT FROM AUTHOR]

The article discusses the integration of arXiv preprints into the zbMATH Open database, which has increased the number of open access documents available. The authors explain the editorial policies and technical challenges involved in this integration, including matching preprints with published versions and author disambiguation. They also highlight the benefits of including arXiv preprints, such as enhancing visibility and providing insights into the publication process. The article concludes by discussing future challenges and potential developments for this integration. [Extracted from the article]

Technical Q&A sites, such as Stack Overflow and Ask Ubuntu, have been widely utilized by software engineers to seek support for development challenges. However, not all the raised questions get instant feedback, and the retrieved answers can vary in quality. The users can hardly avoid spending much time before solving their problems. Prior studies propose approaches to automatically recommend answers for the question posts on technical Q&A sites. However, the lengthiness and the lack of background knowledge issues limit the performance of answer recommendation on these sites. The irrelevant sentences in the posts may introduce noise to the semantics learning and prevent neural models from capturing the gist of texts. The lexical gap between question and answer posts further misleads current models to make failure recommendations. From this end, we propose a novel neural network named TopicAns for answer selection on technical Q&A sites. TopicAns aims at learning high-quality representations for the posts in Q&A sites with a neural topic model and a pre-trained model. This involves three main steps: (1) generating topic-aware representations of Q&A posts with the neural topic model, (2) incorporating the corpus-level knowledge from the neural topic model to enhance the deep representations generated by the pre-trained language model, and (3) determining the most suitable answer for a given query based on the topic-aware representation and the deep representation. Moreover, we propose a two-stage training technique to improve the stability of our model. We conduct comprehensive experiments on four benchmark datasets to verify our proposed TopicAns's effectiveness. Experiment results suggest that TopicAns consistently outperforms state-of-the-art techniques by over 30% in terms of Precision@1. [ABSTRACT FROM AUTHOR]