Group based Personalized Search by Integrating Search Behaviour and Friend Network
The DOI matches its Crossref record; 37 of the 37 references it cites were found in a registry or an index.
Abstract
The key to personalized search is to build the user profile based on historical behaviour. To deal with the users who lack historical data, group based personalized models were proposed to incorporate the profiles of similar users when re-ranking the results. However, similar users are mostly found based on simple lexical or topical similarity in search behaviours. In this paper, we propose a neural network enhanced method to highlight similar users in semantic space. Furthermore, we argue that the behaviour-based similar users are still insufficient to understand a new query when user's historical activities are limited. To tackle this issue, we introduce the friend network into personalized search to determine the closeness between users in another way. Since the friendship is often formed based on similar background or interest, there are plenty of personalized signals hidden in the friend network naturally. Specifically, we propose a friend network enhanced personalized search model, which groups the user into multiple friend circles based on search behaviours and friend relations respectively. These two types of friend circles are complementary to construct a more comprehensive group profile for refining the personalization. Experimental results show the significant improvement of our model over existing personalized search models.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“The introduction of Large Language Models (LLMs) has revolutionized many areas of artificial intelligence, showcasing remarkable abilities in tasks that require human-like reasoning, decisionmaking, and language understanding [38].”
From Generative Agents Navigating Digital Libraries (2025) · cites this paper as [38]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 6×
“We have: 𝐶 𝑓 = Transformer𝑚𝑎𝑠𝑘𝑒𝑑 ( [𝐶r,𝑓 ,𝐶b,𝑓 ]), where Transformer𝑚𝑎𝑠𝑘𝑒𝑑 (·) means adding the mask matrix 𝑀 to the weight matrix of the transformer encoder before softmax.”
MethodInfluentialVeličković, P., Casanova, A., Liò, P., Cucurull, G., Romero, A., & Bengio, Y. (2017) · arXiv (Cornell University) · doi:10.17863/cam.48429 · Cited by 8,657
A large-scale evaluation and analysis of personalized search strategies
Dou, Z., Song, R., & Wen, J.-R. (2007) · Proceedings of the 16th international conference on World Wide Web · doi:10.1145/1242572.1242651 · Cited by 530
Self-citationSearchTogether: an interface for collaborative web search
Morris, M. R., & Horvitz, E. (2007) · Proceedings of the 20th annual ACM symposium on User interface software and technology · doi:10.1145/1294211.1294215 · Cited by 423 · cited 1×
“[18] focused on enhancing the quality of traditional web search with collaborative behaviours.”
BackgroundInvestigating behavioral variability in web search
White, R. W., & Drucker, S. M. (2007) · Proceedings of the 16th international conference on World Wide Web · doi:10.1145/1242572.1242576 · Cited by 327
Web search personalization with ontological user profiles
Sieg, A., Mobasher, B., & Burke, R. (2007) · Proceedings of the sixteenth ACM conference on Conference on information and knowledge management · doi:10.1145/1321440.1321515 · Cited by 324 · cited 1×
“The extraction of topic features has undergone a transition from manual design to automatic learning [2, 20, 33].”
BackgroundModeling the impact of short- and long-term behavior on search personalization
Bennett, P. N., White, R. W., Chu, W., Dumais, S. T., Bailey, P., Borisyuk, F., & Cui, X. (2012) · Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval · doi:10.1145/2348283.2348312 · Cited by 300 · cited 6×
“Moreover, we also identify a document as relevant if it is satisfied under the next two queries following [3, 10].”
BackgroundMethodInfluentialPersonalized social search based on the user's social network
Carmel, D., Zwerdling, N., Guy, I., Ofek-Koifman, S., Har'el, N., Ronen, I., Uziel, E., Yogev, S., & Chernov, S. (2009) · Proceedings of the 18th ACM conference on Information and knowledge management · doi:10.1145/1645953.1646109 · Cited by 241 · cited 1×
“[7] constructed the social network from some social applications, and took the social relations into account while ranking.”
BackgroundTeevan, J. B., Dumais, S., & Horvitz, E. (2010) · ACM Transactions on Computer-Human Interaction · doi:10.1145/1721831.1721835 · Cited by 176 · cited 2×
“[22, 24] tried different grouping ways and showed that grouping could identify what users would consider relevant to the query.”
BackgroundMethodEnhancing personalized search by mining and modeling task behavior
White, R. W., Chu, W., Hassan, A., He, X., Song, Y., & Wang, H. (2013) · International World Wide Web Conference (WWW) · doi:10.1145/2488388.2488511 · Cited by 150 · cited 2×
“The extraction of topic features has undergone a transition from manual design to automatic learning [2, 20, 33].”
BackgroundMethod
Research works printed but not linked: 4
- Wenqi Fan, Yao Ma, Qing Li, Yuan He, Yihong Eric Zhao, Jiliang Tang, and Dawei Yin. 2019. Graph Neural Networks for Social Recommendation. In WWW. ACM, 417--426.
- Tomas Mikolov, Quoc V Le, and Ilya Sutskever. 2013. Exploiting similarities among languages for machine translation. arXiv preprint arXiv:1309.4168 (2013). · arXiv
- Maksims Volkovs. 2015. Context models for web search personalization. arXiv preprint arXiv:1502.00527 (2015). · arXiv
- Qiang Wu, Chris JC Burges, Krysta M Svore, and Jianfeng Gao. 2008. Ranking, boosting, and model adaptation. Tecnical Report. Technical Report. MSR-TR-2008--109.
Cited by
From Matching to Generation: A Survey on Generative Information Retrieval
Li, X., Jin, J., Zhou, Y., Zhang, Y., Zhang, P., Zhu, Y., & Dou, Z. (2025) · ACM Transactions on Information Systems · doi:10.1145/3722552 · Cited by 172
Self-citationTwo Tales of Persona in LLMs: A Survey of Role-Playing and Personalization
Tseng, Y.-M., Huang, Y.-C., Hsiao, T.-Y., Chen, W.-L., Huang, C.-W., Meng, Y., & Chen, Y.-N. (2024) · Findings of the Association for Computational Linguistics: EMNLP 2024 · doi:10.18653/v1/2024.findings-emnlp.969 · Cited by 87
Pre-training Methods in Information Retrieval
Fan, Y., Xie, X., Cai, Y., Chen, J., Ma, X., Li, X., Zhang, R., & Guo, J. (2022) · Foundations and Trends® in Information Retrieval · doi:10.1561/1500000100 · Cited by 98
Contrastive Learning of User Behavior Sequence for Context-Aware Document Ranking
Zhu, Y., Nie, J., Dou, Z., Ma, Z., Zhang, X., Du, P., Zuo, X., & Jiang, H. (2021) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3459637.3482243 · Cited by 54
“User historical behavior or interaction history in a session is known to be very useful for understanding the user’s information needs and to rank documents [4, 20, 32, 63].”
BackgroundSelf-citationPre-training for Ad-hoc Retrieval: Hyperlink is Also You Need
Ma, Z., Dou, Z., Xu, W. X., Zhang, X., Jiang, H., Cao, Z., & Wen, J.-R. (2021) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3459637.3482286 · Cited by 51
“In real-world applications, the queries issued by users are often short and ambiguous [27, 40, 59, 61], such as the query “Apple” (Apple fruit or Apple company?).”
Self-citationPSSL: Self-supervised Learning for Personalized Search with Contrastive Sampling
Zhou, Y., Dou, Z., Zhu, Y., & Wen, J.-R. (2021) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3459637.3482379 · Cited by 47
“In recent years, deep learning has been applied to user modeling for personalized search, which is effective in exploring the potential interests of users [12, 19, 23, 40, 43–45].”
MethodSelf-citationUSER: A Unified Information Search and Recommendation Model based on Integrated Behavior Sequence
Yao, J., Dou, Z., Xie, R., Lu, Y., Wang, Z., & Wen, J.-R. (2021) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3459637.3482489 · Cited by 49
“Typically, many deep learning based personalized search models learn a representation of user interests from her search history to re-rank the candidate documents[13, 20, 21, 43, 44, 48, 49].”
Self-citationLearning Implicit User Profile for Personalized Retrieval-Based Chatbot
Qian, H., Dou, Z., Zhu, Y., Ma, Y., & Wen, J.-R. (2021) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3459637.3482269 · Cited by 50
“Besides, the topic of personalization has also been explored in many other scenarios such as personalized search and user modelling [57–59].”
BackgroundSelf-citationA Category-aware Multi-interest Model for Personalized Product Search
Liu, J., Dou, Z., Zhu, Q., & Wen, J.-R. (2022) · International World Wide Web Conference (WWW) · doi:10.1145/3485447.3511964 · Cited by 19
“Previous studies [2, 11, 29–32] have shown that user history is helpful to obtain the explicit user intent and further improve the quality of search results.”
ResultSelf-citationMotifs-based recommender system via hypergraph convolution and contrastive learning
Sun, Y., Zhu, D., Du, H., & Tian, Z. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.09.102 · Cited by 25
“In particular, the emergence of GNNs has accelerated the industrialization process based on graph data research, such as knowledge question answering and dialogue systems[14, 32], recommender systems[2, 15, 27, 33, 50], and intelligent search[4, 21].”
BackgroundMethodCognitive Personalized Search Integrating Large Language Models with an Efficient Memory Mechanism
Zhou, Y., Zhu, Q., Jin, J., & Dou, Z. (2024) · International World Wide Web Conference (WWW) · doi:10.1145/3589334.3645482 · Cited by 52
“A recent shift has seen the rise of deep learning-based techniques in personalized search, demonstrating superior capabilities in learning implicit user interests [1, 9, 31, 36–39].”
BackgroundSelf-citationImproving Personalized Search with Dual-Feedback Network
Deng, C., Zhou, Y., & Dou, Z. (2022) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3488560.3498447 · Cited by 12
“In recent years, with the research on deep learning becoming popular again, many personalization methods [10, 17, 39, 41–45] based on deep learning have significantly improved the search accuracy to a new level.”
BackgroundSelf-citationIncorporating Explicit Subtopics in Personalized Search
Wang, S., Dou, Z., Yao, J., Zhou, Y., & Wen, J.-R. (2023) · International World Wide Web Conference (WWW) · doi:10.1145/3543507.3583488 · Cited by 10
Self-citationIntegrated Personalized and Diversified Search Based on Search Logs
Liu, J., Dou, Z., Nie, J., & Wen, J.-R. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3291006 · Cited by 10
“Recently, Some researchers [31] try to find similar users from social network to augment the representation of current users.”
BackgroundSelf-citationIntent-Oriented Dynamic Interest Modeling for Personalized Web Search
Bai, Y., Zhou, Y., Dou, Z., & Wen, J.-R. (2024) · ACM Transactions on Information Systems · doi:10.1145/3639817 · Cited by 11
“For personalized search, it facilitates the modeling of potential user interest [15, 31, 51, 59, 61–63].”
Self-citationDeep learning methods for LSTM-based personalized search: a comparative analysis
Abri, S., & Abri, R. (2024) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-024-02418-7 · Cited by 7
“For example, Yujia Zhou et al. [33] suggested the group-based personalized search model FNPS, where neural networks are used to build the model, which highlights comparable users in semantic space.”
InfluentialGlobal or Local: Constructing Personalized Click Models for Web Search
Zhang, J., Liu, Y., Mao, J., Xie, X., Zhang, M., Ma, S., & Tian, Q. (2022) · International World Wide Web Conference (WWW) · doi:10.1145/3485447.3511950 · Cited by 11
“Second, according to existing works in personalized search [9, 21, 22, 30], personalization is not consistently effective for different users because they usually have distinct search habits.”
BackgroundUNICON: A Unified Framework for Behavior-Based Consumer Segmentation in E-Commerce
Dibak, M., Vlasov, V., Karessli, N., Dedik, D., Malykh, E., Wasilewski, J., Torres, T., & Ramallo, A. P. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-3-031-76878-1_4 · Cited by 8
PSSL: Self-supervised Learning for Personalized Search with Contrastive SamplingPreprint
Zhou, Y., Dou, Z., Zhu, Y., & Wen, J.-R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.12614 · Cited by 4
“In recent years, deep learning has been applied to user modeling for personalized search, which is effective in exploring the potential interests of users [12, 19, 23, 40, 43–45].”
MethodSelf-citationSocialformer: Social Network Inspired Long Document Modeling for Document Ranking
Zhou, Y., Dou, Z., Yuan, H., & Ma, Z.-Y. (2022) · International World Wide Web Conference (WWW) · doi:10.1145/3485447.3511962 · Cited by 6
“One of the characteristics of the friend circle is that there is often one person at the core who is responsible for connecting people in the entire circle [52].”
BackgroundSelf-citationLearning from the Wisdom of Crowds: Exploiting Similar Sessions for Session Search
Ye, Y., Li, Z., Dou, Z., Zhu, Y., Zhang, C., Wu, S., & Cao, Z. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i4.25607 · Cited by 2
“To address the data sparsity problem, some researchers attempted to introduce long-term interests in users’ previous searches (Guo et al. 2019; Cheng et al. 2021) or leverage social relationships (Zhou et al. 2021) to aggregate users’ profiles for ranking.”
Self-citationHow to personalize and whether to personalize? Candidate documents decide
Liu, W., Zhou, Y., Zhu, Y., & Dou, Z. (2024) · Knowledge and Information Systems · doi:10.1007/s10115-024-02138-y · Cited by 2
“For personalized search, it is usually applied to predict users’ interests [8, 10–12 , 25– 27 ].”
MethodSelf-citationEncoding Group Interests With Persistent Homology for Personalized Search
Meng, Y., Li, R.-H., Qin, H.-C., Wu, X., Duan, H., Lu, Y., & Wang, G.-R. (2024) · IEEE Transactions on Systems, Man & Cybernetics. Systems · doi:10.1109/tsmc.2024.3410029 · Cited by 5
“Second, the topic similarity between the queries and documents used in existing group-based methods [36], [37], [42], [47] may involve too many noisy users.”
BackgroundMethodResultInfluentialGenerative Agents Navigating Digital Libraries
Zerhoudi, S., & Granitzer, M. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-0865-2_14 · Cited by 1
“Understanding user behavior in digital library searches is crucial for improving these systems to better serve user needs [7, 35, 39].”
Yang, Q., & Jiang, J.-G. (2022) · World Automation Congress (WAC) · doi:10.23919/wac55640.2022.9934253 · Cited by 1
“Network circle group has largely enhanced the sphere and efficiency of individual interaction and significantly expanded traditional interpersonal association modes, becoming an important source of origin for current individual information communication and interflow [7, 8].”
BackgroundEffective Personalized Search With Heterogeneous Graph Based Hawkes Process
Wu, X., Qin, H., Li, R.-H., Meng, Y., Duan, H., Lu, Y., Gao, Y., Jin, F., & Wang, G. (2024) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2024.3399606 · Cited by 2
Zhu, D., Sun, Y., Du, H., & Tian, Z. (2021) · arXiv (Cornell University) · Cited by 1
SEERa: A Framework for Community Prediction
Ziaeinejad, S., Samet, S., & Fani, H. (2022) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3511808.3557529
“Also, a dizzying array of topic modeling libraries [5, 16, 26] and an increasing research in Social Information Retrieval (Social IR) and Social Recommendation that integrates social network contexts to enhance rankings and recommendations [19, 20, 32, 33] have been introduced to date.”
BackgroundIntegration Deep Learning Models Into Personalized Search
Abri, R., & Abri, S. (2025) · Engineering cyber-physical systems and critical infrastructures · doi:10.1007/978-3-031-94600-4_9
Fang, Y., & Zeng, G. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3599630
Information Sources for Query Refinement: A Comprehensive Survey
Taheri, Z., Saeedi, M., Kobti, Z., & Fani, H. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-20897-2_54
Generative Agents Navigating Digital Libraries
Zerhoudi, S., & Granitzer, M. (2026) · arXiv · Cited by 1
“Understanding user behavior in digital library searches is crucial for improving these systems to better serve user needs [7, 35, 39].”
Metadata
- Authors
- Zhou, Y., Dou, Z., Wei, B., Xie, R., & Wen, J.-R.
- Affiliations
- Renmin University of China (CN)
- Tencent (China) (CN)
- Venue
- Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval
- Publisher
- ACM
- Published
- 2021-07-11
- Pages
- 92-101
- OpenAlex
- W3153912254
- Cited by
- 29
- References
- 37
- Citations by year
- 2026: 1 · 2025: 3 · 2024: 7 · 2023: 3 · 2022: 8 · 2021: 7
- FWCI
- 5.18
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) (publishedVersion)
- Funders
- Beijing Outstanding Young Scientist Program (NO. BJJWZYJH012019100020098)
- Shandong Provincial Natural Science Foundation (ZR2019ZD06)
- National Natural Science Foundation of China (No. 61872370 and No. 61832017)
- Topics
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Information Systems › Recommender Systems and Techniques
- Physical Sciences › Computer Science › Information Systems › Web Data Mining and Analysis
- Keywords
- personalized search, search behavior, friendship networks, user similarity, semantic similarity, artificial neural networks, user profiles, re-ranking, limited historical data
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.