Automatic Extraction of Opinion-Based Q&A from Online Developer Chats

@article{Chatterjee2021AutomaticEO,
  title={Automatic Extraction of Opinion-Based Q\&A from Online Developer Chats},
  author={Preetha Chatterjee and Kostadin Damevski and Lori L. Pollock},
  journal={2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE)},
  year={2021},
  pages={1260-1272}
}
Virtual conversational assistants designed specifically for software engineers could have a huge impact on the time it takes for software engineers to get help. Research efforts are focusing on virtual assistants that support specific software development tasks such as bug repair and pair programming. In this paper, we study the use of online chat platforms as a resource towards collecting developer opinions that could potentially help in building opinion Q&A systems, as a specialized instance… 

Figures and Tables from this paper

DISCO: A Dataset of Discord Chat Conversations for Software Engineering Research
TLDR
This paper proposes a dataset called DISCO consisting of the one-year public DIScord chat COnversations of four software development communities, and applies a topic modelling technique for extracting the top five general topics that are most discussed in each Discord channel.
BugListener: Identifying and Synthesizing Bug Reports from Collaborative Live Chats
  • Lin Shi, Fangwen Mu, Qing Wang
  • Computer Science
    2022 IEEE/ACM 44th International Conference on Software Engineering (ICSE)
  • 2022
TLDR
A human evaluation study confirms the effectiveness of Bug Listener in generating relevant and accurate bug reports and demonstrates the significant potential of applying BugListener in community-based software development, for promoting bug discovery and quality improvement.
Opinion Mining for Software Development: A Systematic Literature Review
TLDR
The results of the study serve as references to choose suitable opinion mining tools for software development activities and provide critical insights for the further development of opinion mining techniques in the SE domain.
Requirements for Automating Moderation in Community Question-Answering Websites
TLDR
In this short paper, three key aspects are pinpointed: any good approach should consider specific attributes and features related to context, Automated mechanisms should be proposed according to the highly evolving content of Q&A websites, and decisions are best to accompany clear and justifiable explanations.
Bots in software engineering: a systematic mapping study
TLDR
This study focuses on classification of bots used in software engineering, the various dimensions of the characteristics, the more frequently researched area, potential research spaces to be explored and the perception of bots in the developer community.
Exploring the Use of Chatrooms by Developers: An Empirical Study on Slack and Gitter
TLDR
An investigative study using qualitative and quantitative techniques to gain insights on the use of popular modern chatrooms, specifically Slack and Gitter finds that the developers seek knowledge from the chatrooms to obtain timely feedback from experts, and in return share their expertise to build the project community and their reputations.
Opinion Mining for Software Development: A Systematic Literature Review
BIN LIN, Software Institute Università della Svizzera italiana, Switzerland NATHAN CASSEE, Eindhoven University of Technology, The Netherlands ALEXANDER SEREBRENIK, Eindhoven University of
Data driven covid-19 spread prediction based on mobility and mask mandate information
TLDR
A novel data driven approach using LSTM (Long Short Term Memory) neural network model to form a functional mapping of daily new confirmed cases with mobility data which has been quantified from cell phone traffic information and mask mandate information to enable administrations to make informed decisions and make plans for mitigation strategies and changes in hospital resources.
GitHub Discussions: An Exploratory Study of Early Adoption
TLDR
A mixed-methods study based on early adopters of GitHub discussions found that errors, unexpected behavior, and code reviews are prevalent discussion categories and positive sentiment in Discussions is more frequent than in Stack Overflow posts.

References

SHOWING 1-10 OF 82 REFERENCES
Exploratory Study of Slack Q&A Chats as a Mining Source for Software Engineering Tools
TLDR
The study is designed to investigate the availability of information that has been successfully mined from other developer communications, particularly Stack Overflow, and the prevalence of useful information, including API mentions and code snippets with descriptions, and several hurdles that need to be overcome to automate mining that information.
Automatic Mining of Opinions Expressed About APIs in Stack Overflow
TLDR
It is observed that opinions about diverse API aspects are prevalent and offer insights that can shape developers’ perception and decisions related to software development, and built a suite of techniques to automatically mine and categorize opinions about APIs from forum posts.
Development Emails Content Analyzer: Intention Mining in Developer Discussions (T)
TLDR
A novel, semi-supervised approach named DECA (Development Emails Content Analyzer) that uses Natural Language Parsing to classify the content of development emails according to their purpose, identifying email elements that can be used for specific tasks.
Experiences Building an Answer Bot for Gitter
TLDR
GitterAns is presented, a bot that can automatically detect when a developer asks a technical question in a chat and leverages the information present in Q&A forums to provide the developer with possible answers to their question.
Pattern-Based Mining of Opinions in Q&A Websites
TLDR
POME (Pattern-based Opinion MinEr), an approach that leverages natural language parsing and pattern-matching to classify Stack Overflow sentences referring to APIs according to seven aspects and to determine their polarity, is proposed.
Automating Intention Mining
TLDR
A convolution neural network (CNN)-based approach to automatically classify sentences into different categories of intentions is proposed and investigated and applied to improve an automated software engineering task, in which the proposed approach to rectify misclassified issue reports is used to reduce the bias introduced by such data to other studies.
Detecting speech act types in developer question/answer conversations during bug repair
TLDR
A ``Wizard of Oz'' experiment with 30 professional programmers, in which the programmers fix bugs for two hours, and use a simulated virtual assistant for help, and an open coding manual annotation procedure to identify the speech act types in the conversations.
Extracting problematic API features from forum discussions
TLDR
This paper investigates ways to extract problematic API features that are discussed as a source of difficulty in each thread, using natural language processing and sentiment analysis techniques and chooses a negative sentiment sentence and its close neighbors as a unit for extracting API features.
Automatic summarization of API reviews
  • Gias Uddin, F. Khomh
  • Computer Science
    2017 32nd IEEE/ACM International Conference on Automated Software Engineering (ASE)
  • 2017
TLDR
It was found that developers were interested to use the proposed summaries much more frequently than other summaries and that while combined with Stack Overflow, Opiner helped developers to make the right decision with more accuracy and confidence and in less time.
Finding relevant answers in software forums
TLDR
A semantic search engine framework to process software threads and recover relevant answers according to user queries and infer semantic tags of posts in the software forum threads and utilize these tags to recover relevant answer posts is provided.
...
...