Eliciting Auxiliary Information for Cold Start User Recommendation: A Survey
Source abstract
Abstract
Recommender systems suggest items of interest to users based on their preferences. These preferences are typically generated from user ratings of the items. If there are no ratings for a certain user or item, it is said that there is a cold start problem, which leads to unreliable recommendations. Existing studies that reviewed and examined cold start in recommender systems have not explained the process of deriving and obtaining the auxiliary information needed for cold start recommendation. This study surveys the existing literature in order to explain the various approaches and techniques employed by researchers and the challenges associated with deriving and obtaining the auxiliary information necessary for cold start recommendation. Results show that auxiliary information for cold start recommendation is obtained by adapting traditional filtering and matrix factorization algorithms typically with machine learning algorithms to build learning prediction models. The understanding of similar or connected user profiles can be used as auxiliary information for building cold start user profile to enable similar recommendations in social networks. Similar users are clustered into sub-groups so that a cold start user could be allocated and inferred to a sub-group having similar profiles for recommendations. The key challenges of the process for obtaining the auxiliary information involve: (1) two separate recommendation processes of conversion from pure cold start to warm start before eliciting the auxiliary information; (2) the obtained implicit auxiliary information is usually ranked and sieved in order to select the top rated and reliable auxiliary information for the recommendation. This study also found that cold start user recommendation has frequently been researched in the entertainment domain, typically using music and movie data, while little research has been carried out in educational institutions and academia, or with cold start for mobile applications.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Recommender Systems and Techniques · Advanced Bandit Algorithms Research · Expert finding and Q&A systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer System & Technology, Faculty of Computer Science and Information Technology, Universiti Malaya, Kuala Lumpur 50603, Malaysia
Department of Software Engineering, Faculty of Computer Science and Information Technology, Bayero University Kano, Kano 3011, Nigeria
Department of Software Engineering, Faculty of Computer Science and Information Technology, Universiti Malaya, Kuala Lumpur 50603, Malaysia
Funding
University of Malaya
References (100+)
Show source-provided references
1. Manouselis, N., Drachsler, H., Verbert, K., and Duval, E. (2012). Recommender Systems for Learning, Springer Science & Business Media.10.1007/978-1-4614-4361-2 ↗
2. Recommender systems
3. Ricci, F., Rokach, L., and Shapira, B. (2011). Introduction to recommender systems handbook. Recommender Systems Handbook, Springer.10.1007/978-0-387-85820-3 ↗
4. Desrosiers, C., and Karypis, G. (2011). A comprehensive survey of neighborhood-based recommendation methods. Recommender Systems Handbook, Springer.10.1007/978-0-387-85820-3_4 ↗
5. Koren, Y., and Bell, R. (2015). Advances in collaborative filtering. Recommender Systems Handbook, Springer.10.1007/978-1-4899-7637-6_3 ↗
6. Sun, M., Li, F., Lee, J., Zhou, K., Lebanon, G., and Zha, H. (2013, January 4–8). Learning multiple-question decision trees for cold-start recommendation. Proceedings of the Sixth ACM International Conference on Web Search and Data Mining, Rome, Italy.10.1145/2433396.2433451 ↗
7. Miranda, T., Claypool, M., Gokhale, A., Mir, T., Murnikov, P., Netes, D., and Sartin, M. (1999). Combining content-based and collaborative filters in an online newspaper. Proceedings of the ACM SIGIR Workshop on Recommender Systems, Worchester Polytechnic Institute.
8. A taxonomy of recommender agents on the internet10.1023/A:1022850703159 ↗
9. Facing the cold start problem in recommender systems10.1016/j.eswa.2013.09.005 ↗
10. Cold-start problem in collaborative recommender systems: Efficient methods based on ask-to-rate technique10.2498/cit.1002223 ↗
11. Interactive recommender systems: A survey of the state of the art and future research challenges and opportunities10.1016/j.eswa.2016.02.013 ↗
12. Resolving data sparsity and cold start problem in collaborative filtering recommender system using linked open data10.1016/j.eswa.2020.113248 ↗
13. Social network data to alleviate cold-start in recommender system: A systematic review10.1016/j.ipm.2018.03.004 ↗
14. Dealing with the new user cold-start problem in recommender systems: A comparative review10.1016/j.is.2014.10.001 ↗
15. A systematic literature review of sparsity issues in recommender systems10.1007/s13278-020-0626-2 ↗
16. Cross domain recommender systems: A systematic literature review10.1145/3073565 ↗
17. Deep learning based recommender system: A survey and new perspectives10.1145/3158369 ↗
18. Haruna, K., Akmar Ismail, M., Suhendroyono, S., Damiasih, D., Pierewan, A.C., Chiroma, H., and Herawan, T. (2017). Context-aware recommender system: A review of recent developmental process and future research direction. Appl. Sci., 7.10.3390/app7121211 ↗
19. Xu, B., Bu, J., Chen, C., and Cai, D. (2012, January 16–20). An exploration of improving collaborative recommender systems via user-item subgroups. Proceedings of the 21st International Conference on World Wide Web, Lyon, France.10.1145/2187836.2187840 ↗
20. Koren, Y. (2008, January 24–27). Factorization meets the neighborhood: A multifaceted collaborative filtering model. Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Las Vegas, NV, USA.10.1145/1401890.1401944 ↗
21. Collaborative error-reflected models for cold-start recommender systems10.1016/j.dss.2011.02.015 ↗
22. A collaborative filtering approach to mitigate the new user cold start problem10.1016/j.knosys.2011.07.021 ↗
23. Zhang, M., Tang, J., Zhang, X., and Xue, X. (2014, January 6–11). Addressing cold start in recommender systems: A semi-supervised co-training algorithm. Proceedings of the 37th International ACM SIGIR Conference on Research & Development in Information Retrieval, Gold Coast, QLD, Australia.10.1145/2600428.2609599 ↗
24. Simultaneous co-clustering and learning to address the cold start problem in recommender systems10.1016/j.knosys.2015.02.016 ↗
25. Merging trust in collaborative filtering to alleviate data sparsity and cold start10.1016/j.knosys.2013.12.007 ↗
26. Collaborative filtering and deep learning based recommendation system for cold start items10.1016/j.eswa.2016.09.040 ↗
27. Duricic, T., Lacic, E., Kowald, D., and Lex, E. (2018, January 2). Trust-based collaborative filtering: Tackling the cold start problem using regular equivalence. Proceedings of the 12th ACM Conference on Recommender Systems, Vancouver, BC, Canada.10.1145/3240323.3240404 ↗
28. HRS-CE: A hybrid framework to integrate content embeddings in recommender systems for cold start items10.1016/j.jocs.2018.09.008 ↗
29. Social recommendation with cross-domain transferable knowledge10.1109/TKDE.2015.2432811 ↗
30. Social-group-based ranking algorithms for cold-start video recommendation10.1007/s41060-016-0015-0 ↗
31. Hannech, A., Adda, M., and Mcheick, H. (2016, January 13–15). Cold-start recommendation strategy based on social graphs. Proceedings of the 2016 IEEE 7th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON), Vancouver, BC, Canada.10.1109/IEMCON.2016.7746324 ↗
32. Your neighbors alleviate cold-start: On geographical neighborhood influence to collaborative web service QoS prediction10.1016/j.knosys.2017.10.001 ↗
33. A survey of recommender systems based on deep learning10.1109/ACCESS.2018.2880197 ↗
34. DNNRec: A novel deep learning based hybrid recommender system10.1016/j.eswa.2019.113054 ↗
35. AutoTrustRec: Recommender system with social trust and deep learning using autoEncoder10.1007/s11042-020-08932-4 ↗
36. Matrix factorization model in collaborative filtering algorithms: A survey10.1016/j.procs.2015.04.237 ↗
37. Xue, H.-J., Dai, X., Zhang, J., Huang, S., and Chen, J. (2017, January 19–25). Deep Matrix Factorization Models for Recommender Systems. Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, Melbourne, Australia.10.24963/ijcai.2017/447 ↗
38. Addressing the user cold start with cross-domain collaborative filtering: Exploiting item metadata in matrix factorization10.1007/s11257-018-9217-6 ↗
39. Bi, Y., Song, L., Yao, M., Wu, Z., Wang, J., and Xiao, J. (2020, January 25–30). A Heterogeneous Information Network based Cross Domain Insurance Recommendation System for Cold Start Users. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event.10.1145/3397271.3401426 ↗
40. Improving matrix factorization recommendations for examples in cold start10.1016/j.eswa.2015.04.071 ↗
41. N-dimensional Markov random field prior for cold-start recommendation10.1016/j.neucom.2015.12.099 ↗
42. Joint Personalized Markov Chains with social network embedding for cold-start recommendation10.1016/j.neucom.2019.12.046 ↗
43. Chou, S.-Y., Yang, Y.-H., Jang, J.-S.R., and Lin, Y.-C. (2016, January 15–19). Addressing cold start for next-song recommendation. Proceedings of the 10th ACM Conference on Recommender Systems, Boston, MA, USA.10.1145/2959100.2959156 ↗
44. Connecting social media to e-commerce: Cold-start product recommendation using microblogging information10.1109/TKDE.2015.2508816 ↗
45. Improving top-n recommendation for cold-start users via cross-domain information10.1145/2724720 ↗
46. A cross-domain recommendation mechanism for cold-start users based on partial least squares regression
47. Zhu, F., Wang, Y., Chen, C., Liu, G., Orgun, M., and Wu, J. (arXiv, 2020). A deep framework for cross-domain and cross-system recommendations, arXiv.
48. Barjasteh, I., Forsati, R., Masrour, F., Esfahanian, A.-H., and Radha, H. (2015, January 16–20). Cold-start item and user recommendation with decoupled completion and transduction. Proceedings of the 9th ACM Conference on Recommender Systems, Vienna, Austria.10.1145/2792838.2800196 ↗
49. Rana, C.A.Q., Salima, H., Usama, F., and Hammam, C. (2014, January 23–25). From a “cold” to a “warm” start in recommender systems. Proceedings of the 2014 IEEE 23rd International WETICE Conference, Parma, Italy.
50. CHRS: Cold start recommendation across multiple heterogeneous information networks10.1109/ACCESS.2017.2726339 ↗
51. Kumbhar, N., and Belerao, K. (2017, January 1–18). Microblogging Reviews Based Cross-Lingual Sentimental Classification for Cold-Start Product Recommendation. Proceedings of the 2017 International Conference on Computing, Communication, Control and Automation (ICCUBEA), Pune, India.10.1109/ICCUBEA.2017.8463697 ↗
52. Enabling kernel-based attribute-aware matrix factorization for rating prediction10.1109/TKDE.2016.2641439 ↗
53. Roy, S., and Guntuku, S.C. (2016, January 15–19). Latent factor representations for cold-start video recommendation. Proceedings of the 10th ACM Conference on Recommender Systems, Boston, MA, USA.10.1145/2959100.2959172 ↗
54. Jointly modeling content, social network and ratings for explainable and cold-start recommendation10.1016/j.neucom.2016.03.070 ↗
55. Xu, X., and Yuan, D. (2017, January 28–30). A novel matrix factorization recommendation algorithm fusing social trust and behaviors in micro-blogs. Proceedings of the 2017 IEEE 2nd International Conference on Cloud Computing and Big Data Analysis (ICCCBDA), Chengdu, China.
56. Tomeo, P., Fernández-Tobías, I., Di Noia, T., and Cantador, I. (2016, January 14–16). Exploiting linked open data in cold-start recommendations with positive-only feedback. Proceedings of the 4th Spanish Conference on Information Retrieval, Granada, Spain.10.1145/2934732.2934745 ↗
57. Ostuni, V.C., Di Noia, T., Di Sciascio, E., and Mirizzi, R. (2013, January 12–16). Top-n recommendations from implicit feedback leveraging linked open data. Proceedings of the 7th ACM Conference on Recommender Systems, Hong Kong, China.10.1145/2507157.2507172 ↗
58. Meymandpour, R., and Davis, J.G. (2015, January 27–30). Enhancing Recommender Systems Using Linked Open Data-Based Semantic Analysis of Items. Proceedings of the 3rd Australasian Web Conference (AWC 2015), Sydney, Australia.
59. Nazari, Z., Charbuillet, C., Pages, J., Laurent, M., Charrier, D., Vecchione, B., and Carterette, B. (2015, January 27–30). Recommending Podcasts for Cold-Start Users Based on Music Listening and Taste. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, Sydney, Australia.
60. Kim, B.S., Kim, H., Lee, J., and Lee, J.-H. (2014, January 3–6). Improving a recommender system by collective matrix factorization with tag information. Proceedings of the 2014 Joint 7th International Conference on Soft Computing and Intelligent Systems (SCIS) and 15th International Symposium on Advanced Intelligent Systems (ISIS), Kitakyushu, Japan.10.1109/SCIS-ISIS.2014.7044855 ↗
61. Aggarwal, C.C. (2016). Neighborhood-based collaborative filtering. Recommender Systems, Springer.10.1007/978-3-319-29659-3_2 ↗
62. An effective privacy preserving algorithm for neighborhood-based collaborative filtering10.1016/j.future.2013.07.019 ↗
63. Alleviating the cold-start problem by incorporating movies facebook pages10.1007/s10586-014-0355-2 ↗
64. Exploiting syntactic and neighbourhood attributes to address cold start in tag recommendation10.1016/j.ipm.2018.12.009 ↗
65. Elahi, M., Hosseini, R., Rimaz, M.H., Moghaddam, F.B., and Trattner, C. (2020, January 13–15). Visually-Aware Video Recommendation in the Cold Start. Proceedings of the 31st ACM Conference on Hypertext and Social Media, Virtual Event.10.1145/3372923.3404778 ↗
66. Baeza-Yates, R., Jiang, D., Silvestri, F., and Harrison, B. (2015, January 2–6). Predicting the next app that you are going to use. Proceedings of the eighth ACM International Conference on Web Search and Data Mining, Shanghai, China.10.1145/2684822.2685302 ↗
67. Liu, J., Shi, J., Cai, W., Liu, B., Pan, W., Yang, Q., and Ming, Z. (2017, January 27). Transfer Learning from APP Domain to News Domain for Dual Cold-Start Recommendation. Proceedings of the RecSysKTL, Como Italy.
68. An app usage recommender system: Improving prediction accuracy for both warm and cold start users10.1007/s00530-018-0601-1 ↗
69. From fingerprint to footprint: Cold-start location recommendation by learning user interest from app data10.1145/3314413 ↗
70. Context-aware recommender systems in mobile environment: On the road of future research10.1016/j.is.2017.09.001 ↗
71. Woerndl, W., Huebner, J., Bader, R., and Gallego-Vico, D. (2011, January 23–27). A model for proactivity in mobile, context-aware recommender systems. Proceedings of the Fifth ACM Conference on Recommender Systems, Chicago, IL, USA.10.1145/2043932.2043981 ↗
72. Context-aware recommender systems in mobile scenarios10.4018/jitwe.2009010105 ↗
73. Bouneffouf, D., Bouzeghoub, A., and Gançarski, A.L. (2012, January 12–15). A contextual-bandit algorithm for mobile context-aware recommender system. Proceedings of the International Conference on Neural Information Processing, Doha, Qatar.10.1007/978-3-642-34487-9_40 ↗
74. Bouneffouf, D., Bouzeghoub, A., and Gançarski, A.L. (2012, January 29). Hybrid-ε-greedy for mobile context-aware recommender system. Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mining, Kuala Lumpur, Malaysia.10.1007/978-3-642-30217-6_39 ↗
75. AI-based mobile context-aware recommender systems from an information management perspective: Progress and directions10.1016/j.knosys.2021.106740 ↗
76. Khan, A., Ahmad, A., Rahman, A.U., and Alkhalil, A. (2020). A mobile cloud framework for context-aware and portable recommender system for smart markets. Smart Infrastructure and Applications, Springer.10.1007/978-3-030-13705-2_12 ↗
77. Lin, J., Sugiyama, K., Kan, M.-Y., and Chua, T.-S. (2014, January 6–11). New and improved: Modeling versions to improve app recommendation. Proceedings of the 37th International ACM SIGIR Conference on Research & Development in Information Retrieval, Gold Coast, QLD, Australia.10.1145/2600428.2609560 ↗
78. Liu, B., Kong, D., Cen, L., Gong, N.Z., Jin, H., and Xiong, H. (2015, January 2–6). Personalized mobile app recommendation: Reconciling app functionality and user privacy preference. Proceedings of the Eighth ACM International Conference on Web Search and Data Mining, Shanghai, China.10.1145/2684822.2685322 ↗
79. Cross-platform app recommendation by jointly modeling ratings and texts10.1145/3017429 ↗
80. Lin, J., Sugiyama, K., Kan, M.-Y., and Chua, T.-S. (August, January 28). Addressing cold-start in app recommendation: Latent user models constructed from twitter followers. Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval, Dublin, Ireland.
81. Bayesian Additive Matrix Approximation for Social Recommendation
82. Exploring users’ internal influence from reviews for social recommendation10.1109/TMM.2018.2863598 ↗
83. Social recommendation: A review10.1007/s13278-013-0141-9 ↗
84. Victor, P., De Cock, M., and Cornelis, C. (2011). Trust and recommendations. Recommender Systems Handbook, Springer.10.2991/978-94-91216-08-4_5 ↗
85. Wang, X., Lu, W., Ester, M., Wang, C., and Chen, C. (2016, January 24–28). Social recommendation with strong and weak ties. Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, Indianapolis, IN, USA.10.1145/2983323.2983701 ↗
86. New technique to alleviate the cold start problem in recommender systems using information from social media and random decision forests10.1016/j.ins.2020.05.071 ↗
87. Addressing the cold-start problem in location recommendation using geo-social correlations10.1007/s10618-014-0343-4 ↗
88. Alleviating the new user problem in collaborative filtering by exploiting personality information10.1007/s11257-016-9172-z ↗
89. Using community preference for overcoming sparsity and cold-start problems in collaborative filtering system offering soft ratings10.1016/j.elerap.2017.10.002 ↗
90. Facebook single and cross domain data for recommendation systems10.1007/s11257-012-9128-x ↗
91. Integrating machine learning into item response theory for addressing the cold start problem in adaptive learning systems10.1016/j.compedu.2019.04.009 ↗
92. Salem, Y., Hong, J., and Liu, W. (November, January 29). CSFinder: A cold-start friend finder in large-scale social networks. Proceedings of the 2015 IEEE International Conference on Big Data (Big Data), Santa Clara, CA, USA.10.1109/BigData.2015.7363813 ↗
93. Neural semantic personalized ranking for item cold-start recommendation10.1007/s10791-017-9295-9 ↗
94. A probabilistic model for recommending to new cold-start non-registered users10.1016/j.ins.2016.10.009 ↗
95. Combining community-based knowledge with association rule mining to alleviate the cold start problem in context-aware recommender systems10.1016/j.eswa.2018.01.044 ↗
96. CrowdStart: Warming up cold-start items using crowdsourcing10.1016/j.eswa.2019.07.030 ↗
97. Zhang, X., Yuan, X., Li, Y., and Zhang, Y. (2019, January 21–25). Cold-Start Representation Learning: A Recommendation Approach with Bert4Movie and Movie2Vec. Proceedings of the 27th ACM International Conference on Multimedia, Nice, France.10.1145/3343031.3356070 ↗
98. InNetGAN: Inception Network-Based Generative Adversarial Network for Denoising Low-Dose Computed Tomography10.1155/2021/9975762 ↗
99. Kulathilake, K.S.H., Abdullah, N.A., Sabri, A.Q.M., and Lai, K.W. (2021). A review on Deep Learning approaches for low-dose Computed Tomography restoration. Complex Intell. Syst., 1–33.10.1007/s40747-021-00405-x ↗
100. Characterizing context-aware recommender systems: A systematic literature review10.1016/j.knosys.2017.11.003 ↗