Question Answering Semantic Matching-Based Expert Recommendation Method for New Questions in Knowledge Community

DU Jun-wei; ZOU Shu-lin; LI Hao-jie; JIANG Feng; YU Xu; HU Qiang

doi:10.12263/DZXB.20220197

您当前的位置：

首页 >

文章列表页 >

Question Answering Semantic Matching-Based Expert Recommendation Method for New Questions in Knowledge Community

PAPERS | 更新时间：2025-12-08

- Question Answering Semantic Matching-Based Expert Recommendation Method for New Questions in Knowledge Community
- ACTA ELECTRONICA SINICA Vol. 51, Issue 7, Pages: 1875-1888(2023)
- 作者机构：
  
  青岛科技大学信息科学技术学院，山东青岛266061
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(61973180;6217072142);Natural Science Foundation of Shandong Province(ZR2021MF092;ZR2019MF014;ZR2019MF033;ZR2022MF326)
- DOI：10.12263/DZXB.20220197
  CLC： TP319
- Received：22 February 2022，
  
  Revised：2022-10-07，
  
  Published：25 July 2023
- 稿件说明：
移动端阅览
杜军威,邹树林,李浩杰等.基于问答语义匹配的知识社区新问题专家推荐方法[J].电子学报,2023,51(07):1875-1888.

DU Jun-wei,ZOU Shu-lin,LI Hao-jie,et al.Question Answering Semantic Matching-Based Expert Recommendation Method for New Questions in Knowledge Community[J].ACTA ELECTRONICA SINICA,2023,51(07):1875-1888.
杜军威,邹树林,李浩杰等.基于问答语义匹配的知识社区新问题专家推荐方法[J].电子学报,2023,51(07):1875-1888. DOI： 10.12263/DZXB.20220197.

DU Jun-wei,ZOU Shu-lin,LI Hao-jie,et al.Question Answering Semantic Matching-Based Expert Recommendation Method for New Questions in Knowledge Community[J].ACTA ELECTRONICA SINICA,2023,51(07):1875-1888. DOI： 10.12263/DZXB.20220197.

摘要

传统的知识社区专家推荐方法采用文本相似度匹配机理，并基于问题或专家描述来构建专家特征.这些方法没有利用问题与答案的语义匹配关系，因此难以充分挖掘专家回答问题的能力特征，影响推荐性能.提出一种基于综合历史和当前问答语义匹配的知识社区新问题的专家推荐方法（History-Now Semantics Expert RECommendation model，HNS-EREC）.首先，采用反馈评价和负采样技术来处理数据集中的两类不平衡现象；其次，基于问答语义来提取专家回答问题能力特征；最后，提出一种基于问答语义匹配的History-Now联合专家推荐模型，该模型能够实现面向专家的历史问答和当前问答的语义联合学习.实验结果表明，相对于其他方法，本文所提出的HNS-EREC方法在新问题专家推荐方面具有显著的优势.

Abstract

The traditional knowledge community expert recommendation methods adopt the mechanism of text similarity matching

and construct expert features based on questions or expert descriptions. These methods do not take advantage of the semantic matching relationship between questions and answers

hence it is difficult to fully exploit the features of experts' abilities to answer questions

which will affect the recommendation performance. In this paper

we propose a question answering semantic matching-based expert recommendation method

called History-Now Semantics Expert RECommendation model (HNS-EREC)

for new questions in knowledge community. First

the feedback evaluation and negative sampling techniques are used to handle two types of imbalances in data sets; second

the features of experts' abilities to answer questions are extracted based on question answering semantics; finally

a history-now joint expert recommendation model based on question answering semantic matching is proposed

which can realize the semantic joint learning of expert-oriented historical question answering and current question answering. Experimental results show that compared with other methods

the HNS-EREC method has obvious advantages in the expert recommendation for new questions.

关键词

Keywords

references

SRBA I , BIELIKOVA M . A comprehensive survey and classification of approaches for community question answering [J]. ACM Transactions on the Web , 2016 , 10 ( 3 ): 1 - 63 .

CALEFATO F , LANUBILE F , NOVIELLI N . An empirical assessment of best-answer prediction models in technical Q&A sites [J]. Empirical Software Engineering , 2019 , 24 ( 2 ): 854 - 901 .

JIN Z X , ZHANG B W , ZHOU F , et al . Ranking via partial ordering for answer selection [J]. Information Sciences , 2020 , 538 : 358 - 371 .

OLAOSEBIKAN R , AKINWONMI A E , OJOKOH B A , et al . Development of a best answer recommendation model in a community question answering (CQA) system [J]. Intelligent Information Management , 2021 , 13 ( 3 ): 180 - 198 .

WANG X Z , HUANG C R , YAO L N , et al . A survey on expert recommendation in community question answering [J]. Journal of Computer Science and Technology , 2018 , 33 ( 4 ): 625 - 653 .

WANG G , JIAO J , ABRAHAMS A S , et al . ExpertRank: A topic-aware expert finding algorithm for online knowledge communities [J]. Decision Support Systems , 2013 , 54 ( 3 ): 1442 - 1451 .

FU C G . User intimacy model for question recommendation in community question answering [J]. Knowledge-Based Systems , 2020 , 188 : 104844 .

LI M , QI X Y , LI Y , et al . An approach for constructing expert yellow pages for community question answering sites [J]. Expert Systems , 2021 , 38 ( 4 ). DOI: 10.1111/exsy.12684 http://dx.doi.org/10.1111/exsy.12684 .

FU Y P , XIANG R J , LIU Y Q , et al . Finding experts using social network analysis [C]// IEEE/WIC/ACM International Conference on Web Intelligence (WI'07) . Piscataway : IEEE , 2008 : 77 - 80 .

LINDEN G , SMITH B , YORK J . Amazon.com recommendations: Item-to-item collaborative filtering [J]. IEEE Internet Computing , 2003 , 7 ( 1 ): 76 - 80 .

KOREN Y , BELL R , VOLINSKY C . Matrix factorization techniques for recommender systems [J]. Computer , 2009 , 42 ( 8 ): 30 - 37 .

SINGH A P , GORDON G J . Relational learning via collective matrix factorization [C]// Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . New York : ACM , 2008 : 650 - 658 .

HE X N , LIAO L Z , ZHANG H W , et al . Neural collaborative filtering [C]// Proceedings of the 26th International Conference on World Wide Web . Republic and Canton of Geneva . Switzerland : International World Wide Web Conferences Steering Committee , 2017 : 173 - 182 .

TRNECKA M , TRNECKOVA M . Boolean matrix factorization with background knowledge [J]. Knowledge-Based Systems , 2022 , 241 : 108261 .

PAN Y H , HUO Y F , TANG J , et al . Exploiting relational tag expansion for dynamic user profile in a tag-aware ranking recommender system [J]. Information Sciences , 2021 , 545 : 448 - 464 .

LEE D H , SCHLEYER T . MeSH term explosion and author rank improve expert recommendations [J]. AMIA.. Annual Symposium Proceedings. AMIA Symposium , 2010 , 2010 : 412 - 416 .

YAN X H , GUO J F , LAN Y Y , et al . A biterm topic model for short texts [C]// Proceedings of the 22nd International Conference on World Wide Web . New York : ACM , 2013 : 1445 - 1456 .

MOU H K , GENG Q A , JIN J A , et al . An author subject topic model for expert recommendation [M]// Information Retrieval Technology . Cham : Springer International Publishing , 2015 : 83 - 95 .

WANG J , SUN J Q , LIN H F , et al . Convolutional neural networks for expert recommendation in community question answering [J]. Science China Information Sciences , 2017 , 60 ( 11 ): 1 - 9 .

LI J Y , TANG T Y , ZHAO W X , et al . Pretrained language models for text generation: A survey [EB/OL]. ( 2021 )[2022]. https://api.semanticscholar.org/CorpusID:235125595 https://api.semanticscholar.org/CorpusID:235125595 .

BLEI D , NG A , JORDAN M I . Latent dirichlet allocation [J]. Journal of Machine Learning Research , 2003 , 3 : 993 - 1022 .

MOVSHOVITZ-ATTIAS D , MOVSHOVITZ-ATTIAS Y , STEENKISTE P , et al . Analysis of the reputation system and user contributions on a question answering website: StackOverflow [C]// Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining . New York : ACM , 2013 : 886 - 893 .

HINTON G , VINYALS O , DEAN J . Distilling the knowledge in a neural network [EB/OL]. ( 2015 )[2022]. https://arxiv.org/abs/1503.02531 https://arxiv.org/abs/1503.02531

GOU J P , YU B S , MAYBANK S J , et al . Knowledge distillation: A survey [J]. International Journal of Computer Vision , 2021 , 129 ( 6 ): 1789 - 1819 .

PAGE L , BRIN S , MOTWANI R , et al . The PageRank Citation Ranking: Bringing Order to the Web [R]. Stanford : Stanford InfoLab , 1999 .

SUN J K , BANDYOPADHYAY B , BASHIZADE A , et al . ATP: Directed graph embedding with asymmetric transitivity preservation [J]. Proceedings of the AAAI Conference on Artificial Intelligence , 2019 , 33 ( 1 ): 265 - 272 .

LIU C , HAO Y C , SHAN W , et al . Identifying experts in community question answering website based on graph convolutional neural network [J]. IEEE Access , 2020 , 8 : 137799 - 137811 .

BERKANI L , BELKACEM S , OUAFI M , et al . Recommendation of users in social networks: A semantic and social based classification approach [J]. Expert Systems , 2021 , 38 ( 2 ): e12634 .

GHASEMI N , FATOURECHI R , MOMTAZI S . User embedding for expert finding in community question answering [J]. ACM Transactions on Knowledge Discovery from Data , 2021 , 15 ( 4 ): 1 - 16 .

贾俊杰 , 张玉超 , 刘鹏涛 , 等 . 融合偏置的动态专家信任推荐算法 [J]. 电子与信息学报 , 2021 , 43 ( 8 ): 2370 - 2377 .

JIA J J , ZHANG Y C , LIU P T , et al . Fusion bias dynamic expert trust recommendation algorithm [J]. Journal of Electronics & Information Technology , 2021 , 43 ( 8 ): 2370 - 2377 . (in Chinese)

DUAN Z C , XU W H , CHEN Y T , et al . ETBRec: A novel recommendation algorithm combining the double influence of trust relationship and expert users [J]. Applied Intelligence , 2022 , 52 ( 1 ): 282 - 294 .

HUANG C R , YAO L N , WANG X Z , et al . Expert as a service: Software expert recommendation via knowledge domain embeddings in stack overflow [C]// 2017 IEEE International Conference on Web Services (ICWS) . Piscataway : IEEE , 2017 : 317 - 324 .

闫昭 , 项欣光 , 李泽超 . 基于交互序列商品相关性建模的图卷积会话推荐 [J]. 中国科学: 信息科学 , 2022 , 52 ( 6 ): 1069 - 1082 .

YAN Z , XIANG X G , LI Z C . Item correlation modeling in interaction sequence for graph convolutional session recommendation [J]. Scientia Sinica (Informationis) , 2022 , 52 ( 6 ): 1069 - 1082 . (in Chinese)

MOGAVI R H , GUJAR S , MA X , et al . HRCR: Hidden Markov-based reinforcement to reduce churn in question answering forums [C]// Pacific Rim International Conference on Artificial Intelligence . Cham : International Publishing , 2019 : 364 - 376 .

LIU D R , CHEN Y H , KAO W C , et al . Integrating expert profile, reputation and link analysis for expert finding in question-answering websites [J]. Information Processing & Management , 2013 , 49 ( 1 ): 312 - 329 .

HE T Z , GUO C L , CHU Y F , et al . Dynamic user modeling for expert recommendation in community question answering [J]. Journal of Intelligent & Fuzzy Systems , 2020 , 39 ( 5 ): 7281 - 7292 .

ZHENG L , NOROOZI V , YU P S . Joint deep modeling of users and items using reviews for recommendation [C]// Proceedings of the Tenth ACM International Conference on Web Search and Data Mining . New York : ACM , 2017 : 425 - 434 .

RENDLE S . Factorization machines [C]// 2010 IEEE International Conference on Data Mining . Piscataway : IEEE , 2011 : 995 - 1000 .

DEVLIN J , CHANG M W , LEE K , et al . BERT: Pre-training of deep bidirectional transformers for language understanding [EB/OL].( 2018 )[2022]arXiv: 1810 . 04805 . https://arxiv.org/abs/1810.04805 https://arxiv.org/abs/1810.04805 .

GUO H X , LI Y J , SHANG J , et al . Learning from class-imbalanced data: Review of methods and applications [J]. Expert Systems with Applications , 2017 , 73 : 220 - 239 .

NEKOOEIMEHR I , LAI-YUEN S K . Adaptive semi-unsupervised weighted oversampling (A-SUWO) for imbalanced datasets [J]. Expert Systems with Applications , 2016 , 46 : 405 - 416 .

LOYOLA-GONZÁLEZ O , MARTÍNEZ-TRINIDAD J F C O , CARRASCO-OCHOA J A , et al . Cost-sensitive pattern-based classification for class imbalance problems [J]. IEEE Access , 2019 , 7 : 60411 - 60427 .

KABUTOYA Y , IWATA T , SHIOHARA H , et al . Effective question recommendation based on multiple features for question answering communities [J]. Proceedings of the International AAAI Conference on Web and Social Media , 2010 , 4 ( 1 ): 259 - 262 .

KINGMA D , BA J . Adam: A method for stochastic optimization [EB/OL]. ( 2014 )[2022]. https://doi.org/10.48550/arXiv.1412.6980 https://doi.org/10.48550/arXiv.1412.6980 .

CHEN T Q , GUESTRIN C . XGBoost: A scalable tree boosting system [C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . New York : ACM , 2016 : 785 - 794 .

HOCHREITER S , SCHMIDHUBER J . Long short-term memory [J]. Neural Computation , 1997 , 9 ( 8 ): 1735 - 1780 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Imbalanced Ensemble Algorithm Based on Envelope Learning and Hierarchical Structure Consistency Mechanism

Related Author

LI Fan

ZHANG Xiao-heng

LI Yong-ming

WANG Pin

LI Yong-ming

WANG Pin

Related Institution

College of Communication Engineering， Chongqing University

Chongqing Radio & TV University

⁰