The personalized recommendation aims to address the information overload problem, which can find interesting items for users from massive amounts of information. The research paradigm of personalized recommendation evolved from deep neural networks to pre-trained language models (PLMs) like BERT and, more recently, into large language models (LLMs). However, it is always very difficult to find the target item among a massive number of data or information, which is not only time-consuming but also often has low accuracy. In this paper, we propose a Personalized Recommendation method with Clustering via Prompt-tuning (PRCP), a candidate item set is developed and a prompt-tuning model with a designed verbalizer is constructed for recommendation. Specifically, the target users are first selected by the similarity calculation, and items are then clustered by the preferences of similar users to form a candidate item set. Then the prompt-tuning model is introduced to predict the masked label for candidate items, and three different strategies are designed to expand the label word space for verbalizer optimization. Extensive experiments conducted on three datasets validated the effectiveness of the proposed method compared to other state-of-the-art baselines including LLMs.
TakayanagiTIzumiK. Incorporating domain-specific traits into personality-aware recommendations for financial applications. New Gener Comput2024; 42: 635–649.
2.
singhTKumariMGuptaDS. Context-based persuasion analysis of sentiment polarity disambiguation in social media text streams. New Gener Comput2024; 42: 497–531.
3.
ZhuYWuXQiangJ, et al.Representation learning with collaborative autoencoder for personalized recommendation. Expert Syst Appl2021; 186: 115825.
4.
PenhaGHauffC. What does bert know about books, movies and music? probing bert for conversational recommendation. In: Proceedings of the 14th ACM conference on recommender systems, pp.388–397.
5.
ZhuYGengYLiY, et al.Self-adaptive deep asymmetric network for imbalanced recommendation. IEEE Trans Emerg Top Comput Intell2024; 8: 968–980.
6.
SunFLiuJWuJ, et al.Bert4rec: sequential recommendation with bidirectional encoder representations from transformer. In: Proceedings of the 28th ACM international conference on information and knowledge management, pp.1441–1450.
7.
WangLLimEP. Zero-shot next-item recommendation using large pretrained language models. arXiv preprint arXiv:230403153, 2023.
8.
SchickTSchmidHSchützeH. Automatically identifying words that can serve as labels for few-shot text classification. arXiv preprint arXiv:201013641, 2020.
9.
SchickTSchützeH. Exploiting cloze questions for few shot text classification and natural language inference. arXiv preprint arXiv:200107676, 2020.
10.
TeppalwarVSahooKCJaiswalR, et al.A survey on personalized movie recommendation system using machine learning. In: International conference on smart computing and communication, pp.305–314. Springer.
11.
PengSParkDSKimDY, et al.A modern recommendation system survey in the big data era. In: International conference on computer science and its applications and the international conference on ubiquitous information technologies and applications, pp.577–582. Springer.
12.
KorenYRendleSBellR. Advances in collaborative filtering. Recomm Syst Handb2021; 91–142.
13.
PengSSietSIlkhomjonS, et al.Integration of deep reinforcement learning with collaborative filtering for movie recommendation systems. Appl Sci2024; 14: 1155.
14.
YangYZhuYLiY. Personalized recommendation with knowledge graph via dual-autoencoder. Appl Intell2022; 52: 6196–6207.
15.
WangDZhangXYuD, et al.CAME: content-and context-aware music embedding for recommendation. IEEE Trans Neural Netw Learn Syst2020; 32: 1375–1388.
16.
ZhuYGengYLiY, et al.Representation learning: serial-autoencoder for personalized recommendation. Front Comput Sci2024; 18: 184316.
17.
WuXZhouHYaoW, et al.Towards personalized cold-start recommendation with prompts. arXiv preprint arXiv:230617256, 2023.
18.
ZhuYWangYQiangJ, et al.Prompt-learning for short text classification. IEEE Trans Knowl Data Eng2023; 36: 5328–5339.
19.
MinaeeSKalchbrennerNCambriaE, et al.Deep learning–based text classification: a comprehensive review. ACM Comput Surv (CSUR)2021; 54: 1–40.
20.
YangWXieYTanL, et al.Data augmentation for bert fine-tuning in open-domain question answering. arXiv preprint arXiv:190406652, 2019.
21.
WengRYuHHuangS, et al.Acquiring knowledge from pre-trained model to neural machine translation. In: Proceedings of the AAAI conference on artificial intelligence, volume 34., pp.9266–9273.
22.
QiangJLiYZhuY, et al.Lexical simplification with pretrained encoders. In: Proceedings of the AAAI conference on artificial intelligence, volume 34, pp.8649–8656.
MaXWangZNgP, et al.Universal text representation from bert: an empirical study. arXiv preprint arXiv:191007973, 2019.
25.
JawaharGSagotBSeddahD. What does bert learn about the structure of language? In: ACL 2019-57th Annual meeting of the association for computational linguistics.
26.
YuanFHeXKaratzoglouA, et al.Parameter-efficient transfer from sequential behaviors for user modeling and recommendation. In: Proceedings of the 43rd International ACM SIGIR conference on research and development in information retrieval, pp.1469–1478.
27.
YaoTYiXChengDZ, et al.Self-supervised learning for large-scale item recommendations. In: Proceedings of the 30th ACM international conference on information & knowledge management, pp.4321–4330.
28.
WuJWangXFengF, et al.Self-supervised graph learning for recommendation. In: Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval, pp.726–735.
29.
HouYMuSZhaoWX, et al.Towards universal sequence representation learning for recommender systems. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp.585–593.
30.
ZhouKWangHZhaoWX, et al.S3-rec: Self-supervised learning for sequential recommendation with mutual information maximization. In: Proceedings of the 29th ACM international conference on information & knowledge management, pp.1893–1902.
31.
XiaoCXieRYaoY, et al.UPREC: user-aware pre-training for recommender systems. arXiv preprint arXiv:210210989, 2021.
LiuXJiKFuY, et al.P-tuning v2: prompt tuning can be comparable to fine-tuning universally across scales and tasks. arXiv preprint arXiv:211007602, 2021.
34.
ZhuYShenHLiY, et al.Convert cross-domain classification into few-shot learning: a unified prompt-tuning framework for unsupervised domain adaptation. IEEE Trans Emerg Top Comput Intell2025; 9: 810–821.
35.
BrownTMannBRyderN, et al.Language models are few-shot learners. Adv Neural Inf Process Syst2020; 33: 1877–1901.
36.
GaoTFischAChenD. Making pre-trained language models better few-shot learners. arXiv preprint arXiv:201215723, 2020.
37.
JiangZXuFFArakiJ, et al.How can we know what language models know? Trans Assoc Comput Linguist2020; 8: 423–438.
38.
LiLZhangYChenL. Personalized prompt learning for explainable recommendation. ACM Trans Inform Syst2023; 41: 1–26.
39.
LesterBAl-RfouRConstantN. The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:210408691, 2021.
40.
DengMWangJHsiehCP, et al.Rlprompt: optimizing discrete text prompts with reinforcement learning. arXiv preprint arXiv:220512548, 2022.
41.
HanXZhaoWDingN, et al.PTR: prompt tuning with rules for text classification. AI Open2022; 3: 182–192.
42.
WeiYMoTJiangY, et al.Eliciting knowledge from pretrained language models for prototypical prompt verbalizer. In: International conference on artificial neural networks, pp.222–233. Springer.
43.
HuSDingNWangH, et al.Knowledgeable prompt-tuning: Incorporating knowledge into prompt verbalizer for text classification. arXiv preprint arXiv:210802035, 2021.
44.
NiSKaoHY. KPT++: refined knowledgeable prompt tuning for few-shot text classification. Knowl Based Syst2023; 274: 110647.
45.
HuangHZhangBLiY, et al.Knowledge-enhanced prompt-tuning for stance detection. ACM Trans Asian Low-Resource Language Inform Process2023; 22: 1–20.
46.
WangYXZhangYJ. Nonnegative matrix factorization: a comprehensive review. IEEE Trans Knowl Data Eng2012; 25: 1336–1353.
47.
KorenY. Factorization meets the neighborhood: a multifaceted collaborative filtering model. In: Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining, pp.426–434.
48.
TouvronHMartinLStoneK, et al.Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:230709288, 2023.
