基于同类用户的个性化查询词自动推荐方法

蒋丹阳; 陈洪辉

doi:10.1631/FITEE.1800010

Your Location：

Home >

Browse articles >

基于同类用户的个性化查询词自动推荐方法

常规文章 | Updated：2022-05-19

- 基于同类用户的个性化查询词自动推荐方法
- Cohort-based personalized query auto-completion
- 信息与电子工程前沿（英文） 2019年20卷第9期页码：1246-1258
- Affiliations：
  
  Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, China
- Author bio：
  
  Dan-yang JIANG, E-mail: danyangjiang@nudt.edu.cn
  [ "Hong-hui CHEN, E-mail:chenhonghui@nudt.edu.cn" ]
- Funds：
  
  Project supported by the National Natural Science Foundation of China (No. 61702526), the Defense Industrial Technology Development Program of China (No. JCKY2017204B064), and the National Advanced Research Project of China (No. 6141B0801010b)
- DOI：10.1631/FITEE.1800010
  中图分类号： TP311.5
- 收稿：2018-01-05，
  
  修回：2019-;9-;4，
  
  纸质出版：2019-09
- Accepted：
Scan QR Code
蒋丹阳, 陈洪辉. 基于同类用户的个性化查询词自动推荐方法[J]. 信息与电子工程前沿（英文）, 2019,20(9):1246-1258.

Dan-yang JIANG, Hong-hui CHEN. Cohort-based personalized query auto-completion[J]. Frontiers of Information Technology & Electronic Engineering, 2019, 20(9): 1246-1258.
蒋丹阳, 陈洪辉. 基于同类用户的个性化查询词自动推荐方法[J]. 信息与电子工程前沿（英文）, 2019,20(9):1246-1258. DOI： 10.1631/FITEE.1800010.

Dan-yang JIANG, Hong-hui CHEN. Cohort-based personalized query auto-completion[J]. Frontiers of Information Technology & Electronic Engineering, 2019, 20(9): 1246-1258. DOI： 10.1631/FITEE.1800010.

摘要

查询词自动推荐（query auto-completion，QAC）通过预测查询词前缀对应的完整补全查询词帮助用户构造查询词。大多互联网搜索引擎利用用户的行为信息为用户提供个性化的查询词自动推荐列表。为提高推荐成功率，个性化的QAC方法需获取大量关于用户搜索兴趣和搜索意图的上下文信息。因此，这些方法通常受制于用户数据的稀疏性问题。本文提出利用同类用户的搜索记录解决用户数据的稀疏性问题，并提升个性化QAC方法的推荐性能。首先，通过主题模型得到用户的主题兴趣，建立每个用户的兴趣肖像，然后将兴趣肖像相似的用户聚集起来建立同类用户群。由于传统主题模型不能自动识别同类用户，提出两个同类用户主题模型，将主题建模与同类用户识别包含在同一个模型框架内。根据不同的同类用户识别方法，提供4个不同的基于同类用户的个性化QAC方法。所提个性化QAC方法通过同类用户的上下文信息和查询词的频率对补全的查询词排序。在公开的AOL查询词数据集上进行大量实验，并与不采用同类用户上下文信息的方法进行排序性能对比。实验结果显示，本文提出的基于同类用户的个性化QAC方法能有效解决用户数据稀疏性问题，并且相对于基准方法能大幅提升排序结果准确性。

Abstract

Query auto-completion (QAC) facilitates query formulation by predicting completions for given query prefix inputs. Most web search engines use behavioral signals to customize query completion lists for users. To be effective

such personalized QAC models rely on the access to sufficient context about each user's interest and intentions. Hence

they often suffer from data sparseness problems. For this reason

we propose the construction and application of cohorts to address context sparsity and to enhance QAC personalization. We build an individual's interest profile by learning his/her topic preferences through topic models and then aggregate users who share similar profiles. As conventional topic models are unable to automatically learn cohorts

we propose two cohort topic models that handle topic modeling and cohort discovery in the same framework. We present four cohortbased personalized QAC models that employ four different cohort discovery strategies. Our proposals use cohorts' contextual information together with query frequency to rank completions. We perform extensive experiments on the publicly available AOL query log and compare the ranking effectiveness with that of models that discard cohort contexts. Experimental results suggest that our cohort-based personalized QAC models can solve the sparseness problem and yield significant relevance improvement over competitive baselines.

关键词

Keywords

references

Z Bar-Yossef , , , N Kraus . . Context-sensitive query auto-completion . . Proc 20 th Int Conf on World Wide Web , , 2011 . . p.107 - - 116 . . DOI: 10.1145/1963405.1963424 http://doi.org/10.1145/1963405.1963424 . .

DM Blei , , , AY Ng , , , MI Jordan . . Latent Dirichlet allocation . . J Mach Learn Res , , 2003 . . 3 993 - - 1022 . . . .

CJC Burges , , , KM Svore , , , PN Bennett , , , 等 . . Learning to rank using an ensemble of lambda-gradient models . . J Mach Learn Res , , 2011 . . 14 25 - - 35 . . . .

F Cai , , , M de Rijke . . Learning from homologous queries and semantically related terms for query auto completion . . Inform Process Manag , , 2016a . . 52 ( ( 4 ): ): 628 - - 643 . . DOI: 10.1016/j.ipm.2015.12.008 http://doi.org/10.1016/j.ipm.2015.12.008 . .

F Cai , , , M de Rijke . . A survey of query auto completion in information retrieval . . Found Trends Inform Retr , , 2016b . . 10 ( ( 4 ): ): 273 - - 363 . . DOI: 10.1561/1500000055 http://doi.org/10.1561/1500000055 . .

F Cai , , , R Reinanda , , , M de Rijke . . Diversifying query auto-completion . . ACM Trans Inform Syst , , 2016a . . 34 ( ( 4 ): ): Artilce 25 DOI: 10.1145/2910579 http://doi.org/10.1145/2910579 . .

F Cai , , , SS Liang , , , M de Rijke . . Prefix-adaptive and time-sensitive personalized query auto completion . . IEEE Trans Knowl Data Eng , , 2016b . . 28 ( ( 9 ): ): 2452 - - 2466 . . DOI: 10.1109/TKDE.2016.2568179 http://doi.org/10.1109/TKDE.2016.2568179 . .

X Chen , , , MY Zhou , , , L Carin . . The contextual focused topic model . . Proc 18 th ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining , , 2012 . . p.96 - - 104 . . DOI: 10.1145/2339530.2339549 http://doi.org/10.1145/2339530.2339549 . .

N Fiorini , , , ZY Lu . . Personalized neural language models for real-world query auto completion . . 16 th Annual Conf of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies , , 2018 . . p.208 - - 215 . . DOI: 10.18653/v1/N18-3026 http://doi.org/10.18653/v1/N18-3026 . .

J Gama , , , I Žliobaitė , , , A Bifet , , , 等 . . A survey on concept drift adaptation . . ACM Comput Surv , , 2014 . . 46 ( ( 4 ): ): Article 44 DOI: 10.1145/2523813 http://doi.org/10.1145/2523813 . .

A Hassan , , , RW White . . Personalized models of search satisfaction . . Proc 22 nd ACM Int Conf on Information and Knowledge Management , , 2013 . . p.2009 - - 2018 . . DOI: 10.1145/2505515.2505681 http://doi.org/10.1145/2505515.2505681 . .

JY Jiang , , , PJ Cheng . . Classifying user search intents for query auto-completion . . Proc ACM Int Conf on the Theory of Information Retrieval , , 2016 . . p.49 - - 58 . . DOI: 10.1145/2970398.2970400 http://doi.org/10.1145/2970398.2970400 . .

DF Li , , , Y Ding , , , X Shuai , , , 等 . . Adding community and dynamic to topic models . . J Inform , , 2012 . . 6 ( ( 2 ): ): 237 - - 253 . . DOI: 10.1016/j.joi.2011.11.004 http://doi.org/10.1016/j.joi.2011.11.004 . .

LD Li , , , HB Deng , , , AL Dong , , , 等 . . Exploring query auto-completion and click logs for contextual-aware web search and query suggestion . . Proc 26 th Int Conf on World Wide Web , , 2017a . . p.539 - - 548 . . DOI: 10.1145/3038912.3052593 http://doi.org/10.1145/3038912.3052593 . .

LD Li , , , HB Deng , , , JH Chen , , , 等 . . Learning parametric models for context-aware query auto-completion via Hawkes processes . . Proc 10 th ACM Int Conf on Web Search and Data Mining , , 2017b . . p.131 - - 139 . . DOI: 10.1145/3018661.3018698 http://doi.org/10.1145/3018661.3018698 . .

B Mitra . . Exploring session context using distributed representations of queries and reformulations . . Proc 38 th Int ACM SIGIR Conf on Research and Development in Information Retrieval , , 2015 . . p.3 - - 12 . . DOI: 10.1145/2766462.2767702 http://doi.org/10.1145/2766462.2767702 . .

B Mitra , , , M Shokouhi , , , F Radlinski , , , 等 . . On user interactions with query auto-completion . . Proc 37 th Int ACM SIGIR Conf on Research and Development in Information Retrieval , , 2014 . . p.1055 - - 1058 . . DOI: 10.1145/2600428.2609508 http://doi.org/10.1145/2600428.2609508 . .

MR Morris , , , E Horvitz . . Searchtogether: an interface for collaborative web search . . Proc 20 th Annual ACM Symp on User Interface Software and Technology , , 2007 . . p.3 - - 12 . . DOI: 10.1145/1294211.1294215 http://doi.org/10.1145/1294211.1294215 . .

W Neiswanger , , , C Wang , , , E Xing . . Asymptotically exact, embarrassingly parallel MCMC . . Proc 13 th Conf on Uncertainty in Artificial Intelligence , , 2014 . . p.623 - - 632 . . . .

DH Park , , , R Chiba . . A neural language model for query auto-completion . . Proc 40 th Int ACM SIGIR Conf on Research and Development in Information Retrieval , , 2017 . . p.1189 - - 1192 . . DOI: 10.1145/3077136.3080758 http://doi.org/10.1145/3077136.3080758 . .

G Pass , , , A Chowdhury , , , C Torgeson . . A picture of search . . Proc 1 st Int Conf on Scalable Information Systems , , 2006 . . p.1 DOI: 10.1145/1146847.1146848 http://doi.org/10.1145/1146847.1146848 . .

M Shokouhi . . Learning to personalize query auto-completion . . Proc 36 th Int ACM SIGIR Conf on Research and Development in Information Retrieval , , 2013 . . p.103 - - 112 . . DOI: 10.1145/2484028.2484076 http://doi.org/10.1145/2484028.2484076 . .

M Shokouhi , , , K Radinsky . . Time-sensitive query auto-completion . . Proc 35 th Int ACM SIGIR Conf on Research and Development in Information Retrieval , , 2012 . . p.601 - - 610 . . DOI: 10.1145/2348283.2348364 http://doi.org/10.1145/2348283.2348364 . .

B Smyth , , , E Balfe , , , P Briggs , , , 等 . . Collaborative web search . . Proc 18 th Int Joint Conf on Artificial Intelligence , , 2003 . . p.1417 - - 1419 . . . .

M Steyvers , , , P Smyth , , , M Rosen-Zvi , , , 等 . . Probabilistic author-topic models for information discovery . . Proc 10 th Int Conf on Knowledge Discovery and Data Mining , , 2004 . . p.306 - - 315 . . DOI: 10.1145/1014052.1014087 http://doi.org/10.1145/1014052.1014087 . .

J Teevan , , , MR Morris , , , S Bush . . Discovering and using groups to improve personalized search . . Proc 2 nd ACM Int Conf on Web Search and Data Mining , , 2009 . . p.15 - - 24 . . DOI: 10.1145/1498759.1498786 http://doi.org/10.1145/1498759.1498786 . .

RW White , , , W Chu , , , A Hassan , , , 等 . . Enhancing personalized search by mining and modeling task behavior . . Proc 22 nd Int Conf on World Wide Web , , 2013 . . p.1411 - - 1420 . . DOI: 10.1145/2488388.2488511 http://doi.org/10.1145/2488388.2488511 . .

XD Wu , , , V Kumar , , , JR Quinlan , , , 等 . . Top 10 algorithms in data mining . . Knowl Inform Syst , , 2008 . . 14 ( ( 1 ): ): 1 - - 37 . . DOI: 10.1007/s10115-007-0114-2 http://doi.org/10.1007/s10115-007-0114-2 . .

JY Yan , , , W Chu , , , RW White . . Cohort modeling for enhanced personalized search . . Proc 37 th Int ACM SIGIR Conf on Research and Development in Information Retrieval , , 2014 . . p.505 - - 514 . . DOI: 10.1145/2600428.2609617 http://doi.org/10.1145/2600428.2609617 . .

ZJ Yin , , , LL Cao , , , QQ Gu , , , 等 . . Latent community topic analysis: integration of community discovery with topic modeling . . ACM Trans Intell Syst Technol , , 2012 . . 3 ( ( 4 ): ): Article 63 DOI: 10.1145/2337542.2337548 http://doi.org/10.1145/2337542.2337548 . .

A Zhang , , , A Goyal , , , WZ Kong , , , 等 . . adaQAC: adaptive query auto-completion via implicit negative feedback . . Proc 38 th Int ACM SIGIR Conf on Research and Development in Information Retrieval , , 2015 . . p.143 - - 152 . . DOI: 10.1145/2766462.2767697 http://doi.org/10.1145/2766462.2767697 . .

GQ Zheng , , , JW Guo , , , LC Yang , , , 等 . . Mining topics on participations for community discovery . . Proc 34 th Int ACM SIGIR Conf on Research and Development in Information Retrieval , , 2011 . . p.445 - - 454 . . DOI: 10.1145/2009916.2009977 http://doi.org/10.1145/2009916.2009977 . .

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

暂无数据