Predicting semantically linkable knowledge in developer online forums via convolutional neural network

Bowen Xu, Deheng Ye, Zhenchang Xing, Xin Xia, Guibin Chen, Shanping Li

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

130 Citations (Scopus)


Consider a question and its answers in Stack Overow as a knowledge unit. Knowledge units often contain semantically relevant knowledge, and thus linkable for different purposes, such as duplicate questions, directly linkable for problem solving, indirectly linkable for related information. Recognising different classes of linkable knowledge would support more targeted information needs when users search or explore the knowledge base. Existing methods focus on binary relatedness (i.e., related or not), and are not robust to recognize different classes of semantic relatedness when linkable knowledge units share few words in common (i.e., have lexical gap). In this paper, we formulate the problem of predicting semantically linkable knowledge units as a multiclass classification problem, and solve the problem using deep learning techniques. To overcome the lexical gap issue, we adopt neural language model (word embeddings) and convolutional neural network (CNN) to capture wordand document-level semantics of knowledge units. Instead of using human-engineered classifier features which are hard to design for informal user-generated content, we exploit large amounts of different types of user-created knowledge-unit links to train the CNN to learn the most informative wordlevel and document-level features for the multiclass classification task. Our evaluation shows that our deep-learning based approach significantly and consistently outperforms traditional methods using traditional word representations and human-engineered classifier features.

Original languageEnglish
Title of host publicationASE'16 - Proceedings of the 31st IEEE/ACM International Conference on Automated Software Engineering
Subtitle of host publicationSeptember 3-7, 2016 Singapore, Singapore
EditorsDavid Lo, Sven Apel , Sarfraz Khurshid
Place of PublicationNew York NY USA
PublisherAssociation for Computing Machinery (ACM)
Number of pages12
ISBN (Electronic)9781450338455
Publication statusPublished - 2016
Externally publishedYes
EventAutomated Software Engineering Conference 2016 - Singapore Management University (SMU), Singapore, Singapore
Duration: 3 Sept 20167 Sept 2016
Conference number: 31st (Conference website) (Proceedings)


ConferenceAutomated Software Engineering Conference 2016
Abbreviated titleASE 2016
Internet address


  • Deep learning
  • Link prediction
  • Mining software repositories
  • Multiclass classification
  • Semantic relatedness

Cite this