Entity-level sentiment analysis of issue comments

Ding, Junfeng; Sun, Hailong; Wang, Xu; Liu, Xudong

doi:10.1145/3194932.3194935

Cited by 71 publications

(44 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Despite a relatively large number of works devoted to comparing approaches and methods for sentiment analysis, most of them study only some aspects of solving the problem [5][6][7][8][9][10][11][12]. For example, in [5], the authors compare the approach based on the lexical algorithm from the Apache Hadoop architecture and Stanford coreNLP library with the implementation of recursive neural networks.…”

Section: Related Workmentioning

confidence: 99%

“…However, their paper avoids the comparison of sequential approaches traditionally used in natural language processing. In [6], a mood analysis system was proposed for enterprise software developers. The authors limited themselves to using only a set of vectorizers, classic machine learning models, and a preprocessing stack.…”

Section: обработка информации и управлениеmentioning

confidence: 99%

See 1 more Smart Citation

Generalized approach to sentiment analysis of short text messages in natural language processing

Polyakov¹,

Voskov²,

Abramov³

et al. 2020

ICS

View full text Add to dashboard Cite

Introduction: Sentiment analysis is a complex problem whose solution essentially depends on the context, field of study andamount of text data. Analysis of publications shows that the authors often do not use the full range of possible data transformationsand their combinations. Only a part of the transformations is used, limiting the ways to develop high-quality classification models.Purpose: Developing and exploring a generalized approach to building a model, which consists in sequentially passing throughthe stages of exploratory data analysis, obtaining a basic solution, vectorization, preprocessing, hyperparameter optimization, andmodeling. Results: Comparative experiments conducted using a generalized approach for classical machine learning and deeplearning algorithms in order to solve the problem of sentiment analysis of short text messages in natural language processinghave demonstrated that the classification quality grows from one stage to another. For classical algorithms, such an increasein quality was insignificant, but for deep learning, it was 8% on average at each stage. Additional studies have shown that theuse of automatic machine learning which uses classical classification algorithms is comparable in quality to manual modeldevelopment; however, it takes much longer. The use of transfer learning has a small but positive effect on the classificationquality. Practical relevance: The proposed sequential approach can significantly improve the quality of models under developmentin natural language processing problems.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: обработка информации и управлениеmentioning

confidence: 99%

Generalized approach to sentiment analysis of short text messages in natural language processing

Polyakov¹,

Voskov²,

Abramov³

et al. 2020

ICS

View full text Add to dashboard Cite

show abstract

“…Furthermore, Imtiaz et al [34] directly used emojis as the indicators of developers' sentiments on GitHub. Calefato et al [14] and Ding et al [22] took emoticons into account in their proposed sentiment analysis techniques built on SE-related texts. All of them demonstrated the feasibility of leveraging these emotional cues to benefit sentiment analysis in SE.…”

Section: Emojis In Sentiment Analysismentioning

confidence: 99%

SEntiMoji: an emoji-powered learning approach for sentiment analysis in software engineering

Chen

Cao

Lü

et al. 2019

Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of

View full text Add to dashboard Cite

Sentiment analysis has various application scenarios in software engineering (SE), such as detecting developers' emotions in commit messages and identifying their opinions on Q&A forums. However, commonly used out-of-the-box sentiment analysis tools cannot obtain reliable results on SE tasks and the misunderstanding of technical jargon is demonstrated to be the main reason. Then, researchers have to utilize labeled SE-related texts to customize sentiment analysis for SE tasks via a variety of algorithms. However, the scarce labeled data can cover only very limited expressions and thus cannot guarantee the analysis quality. To address such a problem, we turn to the easily available emoji usage data for help. More specifically, we employ emotional emojis as noisy labels of sentiments and propose a representation learning approach that uses both Tweets and GitHub posts containing emojis to learn sentiment-aware representations for SE-related texts. These emoji-labeled posts can not only supply the technical jargon, but also incorporate more general sentiment patterns shared across domains. They as well as labeled data are used to learn the final sentiment classifier. Compared to the existing sentiment analysis methods used in SE, the proposed approach can achieve significant improvement on representative benchmark datasets. By further contrast experiments, we find that the Tweets make a key contribution to the power of our approach. This finding informs future research not to unilaterally pursue the domain-specific resource, but try to transform knowledge from the open domain through ubiquitous signals such as emojis.

show abstract

“…Their approach apply machine learning techniques and rely on metrics that measure the maintained level to identify and alert users. Machine learning is also used in GitHub to classify user's sentiments in the comments of issues [9,21] and to identify software vulnerabilities [10]. User behavior is also analyzed in other studies.…”

Section: Related Workmentioning

confidence: 99%

Beyond Textual Issues

Borges¹,

Brito²,

Valente³

2019

Proceedings of the XXXIII Brazilian Symposium on Software Engineering

View full text Add to dashboard Cite

Recently, GitHub introduced a new social feature, named reactions, which are "pictorial characters" similar to emoji symbols widely used nowadays in text-based communications. Particularly, GitHub users can use a pre-defined set of such symbols to react to issues and pull requests. However, little is known about the real usage and impact of GitHub reactions. In this paper, we analyze the reactions provided by developers to more than 2.5 million issues and 9.7 million issue comments, in order to answer an extensive list of nine research questions about the usage and adoption of reactions. We show that reactions are being increasingly used by open source developers. Moreover, we also found that issues with reactions usually take more time to be handled and have longer discussions.

show abstract

Entity-level sentiment analysis of issue comments

Cited by 71 publications

References 26 publications

Generalized approach to sentiment analysis of short text messages in natural language processing

Generalized approach to sentiment analysis of short text messages in natural language processing

SEntiMoji: an emoji-powered learning approach for sentiment analysis in software engineering

Beyond Textual Issues

Contact Info

Product

Resources

About