Structures or Texts? A Dynamic Gating Method for Expert Finding in CQA Services

Expert finding plays an important role in community question answering websites. Previously, most works focused on assessing the user expertise scores mainly from their past question-answering semantic features. In this work, we propose a gating mechanism to dynamically combine structural and textua...

Full description

Saved in:
Bibliographic Details
Published inDatabase Systems for Advanced Applications Vol. 10828; pp. 201 - 208
Main Authors Liu, Zhiqiang, Zhang, Yan
Format Book Chapter
LanguageEnglish
Published Switzerland Springer International Publishing AG 2018
Springer International Publishing
SeriesLecture Notes in Computer Science
Subjects
Expert finding
Gating mechanism
Neural Tensor Network
Representation learning
Online AccessGet full text
ISBN331991457X
9783319914572
ISSN0302-9743
1611-3349
DOI10.1007/978-3-319-91458-9_12

Cover

More Information
Summary:Expert finding plays an important role in community question answering websites. Previously, most works focused on assessing the user expertise scores mainly from their past question-answering semantic features. In this work, we propose a gating mechanism to dynamically combine structural and textual representations based on past question-answering behaviors. We also use some user activities including temporal behaviors as the features, which determine the gate values. We evaluate the performance of our method on the well-known question answering sites Stackexchange and Quora. Experiments show that our approach can improve the performance on expert finding tasks.
ISBN:331991457X
9783319914572
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-319-91458-9_12