Detection of Hidden Feature Requests from Massive Chat Messages via Deep Siamese NetworkTechnical
Online chatting is gaining popularity and plays an increasingly significant role in software development. When discussing functionalities, developers might reveal their desired features to other developers. Automated mining techniques towards retrieving feature requests from massive chat messages can benefit the requirements gathering process. But it is quite challenging to perform such techniques because detecting feature requests from dialogues requires a thorough understanding of the contextual information, and it is also extremely expensive on annotating feature-request dialogues for learning. To bridge that gap, we recast the traditional text classification task of mapping single dialog to its class into the task of determining whether two dialogues are similar or not by incorporating few-shot learning. We propose a novel approach, named FRMiner, which can detect feature-request dialogues from chat messages via deep Siamese network. We design a BiLSTM-based dialog model that can learn the contextual information of a dialog in both forward and reverse directions. Evaluation on the real-world projects shows that our approach achieves average precision, recall and F1-score of 88.52%, 88.50% and 88.51%, which confirm that our approach could effectively detect hidden feature requests from chat messages, thus can facilitate gathering comprehensive requirements from the crowd in an automated way.
Tue 7 JulDisplayed time zone: (UTC) Coordinated Universal Time change
08:05 - 09:05 | I6-Empirical Studies and RequirementsJournal First / Software Engineering in Practice / Technical Papers at Silla Chair(s): Ita Richardson Lero - The Irish Software Research Centre and University of Limerick | ||
08:05 8mTalk | What do Programmers Discuss about Deep Learning FrameworksJ1 Journal First Junxiao Han Zhejiang University, Emad Shihab Concordia University, Zhiyuan Wan Zhejiang University, Shuiguang Deng Zhejiang University, Xin Xia Monash University | ||
08:13 12mTalk | Detection of Hidden Feature Requests from Massive Chat Messages via Deep Siamese NetworkTechnical Technical Papers Lin Shi ISCAS, Mingzhe Xing ISCAS, Mingyang Li ISCAS, Yawen Wang ISCAS, Shoubin Li ISCAS, Qing Wang Institute of Software, Chinese Academy of Sciences | ||
08:25 8mTalk | Recognizing lines of code violating company-specific coding guidelines using machine learningJ1 Journal First Miroslaw Ochodek Poznan University of Technology, Regina Hebig Chalmers University of Technology & University of Gothenburg, Wilhelm Meding Ericsson, Gert Frost Grundfos, Miroslaw Staron University of Gothenburg | ||
08:33 12mTalk | Context-aware In-process Crowdworker RecommendationTechnical Technical Papers Junjie Wang Institute of Software, Chinese Academy of Sciences, Ye Yang Stevens institute of technology, Song Wang York University, Yuanzhe Hu Institute of Software, Chinese Academy of Sciences, Dandan Wang Institute of Software, Chinese Academy of Sciences, Qing Wang Institute of Software, Chinese Academy of Sciences | ||
08:45 12mTalk | Using a Context-Aware Approach to Recommend Code Reviewers: Findings from an Industrial Case StudySEIP Software Engineering in Practice Anton Strand Ericsson AB, Markus Gunnarsson Ericsson AB, Ricardo Britto Ericsson / Blekinge Institute of Technology, Muhammad Usman Blekinge Institute of Technology |